You are on page 1of 16

Recapturing Lost Customers

Author(s): Jacquelyn S. Thomas, Robert C. Blattberg and Edward J. Fox
Source: Journal of Marketing Research, Vol. 41, No. 1 (Feb., 2004), pp. 31-45
Published by: American Marketing Association
Stable URL: http://www.jstor.org/stable/30162310
Accessed: 23-11-2017 16:02 UTC

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide
range of content in a trusted digital archive. We use information technology and tools to increase productivity and
facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.

Your use of the JSTOR archive indicates your acceptance of the Terms & Conditions of Use, available at
http://about.jstor.org/terms

American Marketing Association is collaborating with JSTOR to digitize, preserve and
extend access to Journal of Marketing Research

This content downloaded from 193.175.6.21 on Thu, 23 Nov 2017 16:02:55 UTC
All use subject to http://about.jstor.org/terms

Pro. Medill School of Journalism (e-mail: defined as the net present value (NPV) of the customer's jakki@northwestern. tomer obtained from an external list is 23% compared with a 214% return on investment from the reinstatement of a tomer. profitability throughout the customer-firm relationship fessor of Retailing. 23 Nov 2017 16:02:55 UTC All use subject to http://about. In addition to pric- ing strategy.L. Books and articles have been written and busi- nesses have been developed around the central theme of the Industry Defection Rate management and maintenance of customer relationships 22% Internet service providers (see.g. e. to a lost customer.org/terms . the dominant focus of customer relationship management has been customer retention. In some cases. Although progress has been U. The authors assert that customer winback should also be an important part of a cus- tomer relationship management strategy. Edward of lost customers. By simultaneously modeling reacquisition and duration of the second tenure with the firm. FOX* For both academics and practitioners. strategies and tactics developed. Stauss and Friege Journal of Marketing Research 31 Vol. This metric focuses only on the NPV generated after a cus- tomer has been reacquired. Specifically. JACQUELYN S. they also discuss the implications of their findings for target- ing lapsed customers for reacquisition.. an area that has been largely neglected in the marketing literature is customer "winback" strategies. and Robert C.S. Reichheld 1996). Fox is W. long distance (telephone) 30% made in the management of customer relationships. ANNUAL CUSTOMER DEFECTION RATES ment (CRM). Northwestern University. Customer winback focuses on the reinitiation and management of relationships with customers who have lapsed or defected from a firm. and a corn- mon tactic is lowering the price to reacquire a customer. J. THOMAS. and EDWARD J. there German mobile telephone market 25% are still high defection rates. XLI (February 2004). lence and Assistant Professor of Marketing.R. Kellogg Graduate School of Management (e-mail: (Dwyer 1989).edu). Recapturing Lost Customers Loyalty and retention have been the dominant themes Table 1 among scholars interested in customer relationship manage. Customer lifetime value (LTV) is a central profitability met- ric in analysis of customer relationships. when it comes to the recapturing r-blattberg@kellogg.edu).cox. The importance and impact of customer winback defected customers. it is typically *Jacquelyn S. a 20% to 40% chance of successfully repeat-selling customer who has defected. firms engage in extensive efforts to reacquire lapsed customers or defectors. the second lifetime value (SLTV) of the J. Although all aspects of CRM need to be assessed and Adapted from Griffin and Lowenstein (2001). Integrated Marketing Communications Department. Stauss and Friege (1999) make this as a key element in a firm's CRM strategy cannot be under. Research has shown that a firm has a 60% to 70% they find that the net return on investment from a new cus- chance of successfully repeat-selling to an "active" cus. This investiga- tion goes beyond the reacquisition pricing strategy and also examines the optimal pricing strategy when the customer has decided to reinitiate the relationship.21 on Thu. which we have adapted Clothing catalogs 25% Residential tree and lawn care 32% from the work of Griffin and Lowenstein (2001). Table 1. argument even more convincing in a case study in which estimated. Edwin Cox School of Business. and only a 5% to 20% chance of suc- cessfully closing the sale on a brand new customer (Griffin A critical element in the process of firms' recapturing of and Lowenstein 2001). However. Howell Director of the JCPenney Center for Retail Excel- customer (Stauss and Friege 1999) is the metric of interest.6.smu. BLATTBERG. Blattberg is the Polk Bros. 31-45 This content downloaded from 193.northwestern. ROBERT C. shows cus- Newspaper subscriptions 66% tomer defection rates across various industries.175.jstor. Thomas is an associate professor. Customer winback is the process of opportunity for firms to increase or maintain a customer firms' revitalizing relationships with customers who have base is the mining and evaluation of the firm's database of defected.edu). the authors determine that the optimal pricing strategy for their application involves a low reacquisition price and higher prices when customers have been reacquired. These statistics suggest that a key lost customers is the assessment of customer profitability. Southern Methodist University (e-mail: efox@mail.

the ham company. How- firms. mining the optimal price for recapturing a customer is only particularly research that addresses customer reacquisition part of the challenge in firms' customer winback strategy. Kalyanam (1996) shows that dif- next purchases. of Stauss and Friege (1999). they typically presented them with offers that Finally. and regain controls (i. work used to test our theory.e. the profit/ customer (Thomas 2001). Amazon. To stimulate purchase activity. telemarketing efforts. This example illustrates the importance of SLTV to ever. area and has been the subject of little empirical research. engaging in dialogue with the customer to determine the tomer affects the future relationship that a firm has with that appropriate regain offer). (Keaveny 1995). come-back cash incentives) often caused the SLTV for the reacquired customers to be On the surface. Similarly. Some cus. use of pricing to reacquire and retain lapsed customers. the reacquisition of a customer correlates and influences the Our research addresses the three areas of Stauss and reinstated customer-firm relationship.g. sis and our study's limitations. ferent ways of specifying demand can lead to different offers a $10 gift certificate to reactivate customers (Schmid profit-maximizing prices. development demand is typically and determined implementation of a customer recapture by the durationexpecta- program. Deter. For example. In this context.6. we conclude with a general discussion of our analy- were better than the original offer. In subsequent sections. health clubs). Thus. When the original provider approached customers to and examine the financial implications of our analysis..21 on Thu.175. of a recaptured This context cus-benefit that rela- also offers the additional tionship tomer should be the guiding factor. However.g. HoneyBaked. Unlike Stauss and Friege.e. we examine the relationship Friege present a conceptual framework for customer win- between the price used to recapture the customer and the back that entails regain analysis (i. denced by the fact that demand models typically used in tice. ory of restart customer behavior. This service also may change its prices Some firms engage in extensive efforts to recapture over time. we also draw conclusions about tion of a lapsed customers. tomers switched to benefit from the introductory offer of a In the next section. this research domain provides limited insight into the the strategy and tactics of customer reacquisition. present the empirical results. come back. the CRM literature focuses on the individual discounts of up to 25% to customers who have not ordered customer and emphasizes LTV. 23 Nov 2017 16:02:55 UTC All use subject to http://about. Specifically. we present a the- a better offer from the original provider (Marple and Zim. and Self Care. lapses are SLTVclearly identified. the context of our research offers the bene- defected customers or to reactivate lapsed customers. Tra- The focus of our article is on determining how firms ditional pricing research does not focus on the long-term should price customers when reacquiring them and how they relationship between the customer and the firm. Although our data do reacquisition. To recapture lost customers. durations and the Logically. regain actions (i. pric. Prior research has shown that the acquisition of a cus." which they define as the strategies for the recapture of lost customers and the man. A key consideration Friege's (1999) framework in a more rigorous context. which is a relatively new from the company in 18 to 24 months (Kiley 1996). whereas others simply wanted to solicit pricing and CRM. prior We explore these questions in the context of services such research has shown that unfavorable price perceptions have as newspapers and magazine subscriptions and organiza. A common charac. FEBRUARY 2004 (1999) define SLTV as the future value teristicof a recaptured of these cus- services is that the quantity purchased is typ- ically to tomer.. ours in that it explicitly addresses customer winback is that tomer has been reacquired. They explore a concept that The objective of this research is to assess optimal pricing they term "regain management. For fit of explicitly identifying relationship duration. not enable us to determine why the lapse occurred.e. of the customer-firm relation- tions about the potential future value ship. used to estimate the model. reactiva- SLTV AND WINBACK LITERATURE REVIEW tion fees. characterize contracted services. Using observable of defected and restart customers to determine drivers of characteristics about the prior relationship (e. describe the data and variables cations firms engaged in aggressive "come-back" cam. 32 JOURNAL OF MARKETING RESEARCH. behavior of individual customers (for a review. should guide the decisions with respect Although tothese relationships which tend to involve contracts. and SLTV. we model both the reacquisition and the reten- ing. tenure. see Mahajan. the customers should be recaptured and how much should service we analyze allows customers be spent to reac-to defect at any time quire them.g... telecommuni. during the long-distance telephone wars. reacquisition. and we focus explicitly on pric- which lapsed customers are the most profitable targets for ing as a means to recapture customers. the consumer usu. we review the relevant literature on competing provider. and Bass 1993). but it is not example. paigns. the research that is most similar to An equally important decision is how to price when the cus. one seg. without a penalty. 1998). detail the modeling frame- merman 1999). ally benefited. in this analysis is the influence of the customer's relation.org/terms . This is evi- should price them when they have been reacquired. In prac. reacquisition costs (e. process of winning back customers who either give notice to agement of the SLTV of the recaptured customer (i.com offers lapsed customers discounts on their Mueller.. They assert that when it comes one unit of the service. Stauss and restart customer). This content downloaded from 193. Thus. thereby representing a net loss to the provider appropriate foundation on which to base our research. a health care products marketer. offers In contrast.. limited by the pricing and duration constraints that often ment of customers frequently switched providers. Thus. a direct effect on a customer's intention to switch providers tional memberships (e.jstor.e.. duration of lapse). determining which subsequent price when the customer has been reacquired. customers have defected and why). research on dynamic pricing seems an negative. the favored approach is to offer restarts lower prices for pricing research do not monitor the churn or retention the same product. we perform a statistical analysis ship with the firm before reactivation. a terminate or have already ended the relationship. we examine how loss analysis of the regain actions).

. Our research incorpo. The first is critical for targeting. we assert the following: tenures are shorter.versus short-life customers but on the pricing strategy for restart customers who may have eitherAlthough the normative beliefs of direct marketers about long or short prior relationships with the firm. price gains have a larger impact on brand of how much to use the service. Bolton and Lemon (1999) show thata service affects their subsequent attitudes and assessments customers' use of two continuously provided services partly of that service. This raises the There are two basic issues that we address in our theory question. The fina BEHAVIOR ity of this termination is not known at the time when the firm evaluates potential reacquisition candidates. In addition. basis frequency.e. focus is not on long. they draw inferences about the ence can be measured by their prior tenure (which we refe price sensitivity of customers who have longer relationships to as Tenure 1 or first tenure) with the firm. however. we actually estimate price sensitivity. and Staelin (1999 directly.versus find that a customer's level of satisfaction can moderate this short-life customers and then examine the mean price paid result. that is Friege (1999). These two issues are par- Prior research has asserted that with the passage of time. the length of their first tenure with firm is positively related to (a) the reacquisition probability Thus. Mazumdar. Bolton. of and monetar ate customers in those segments value analysis. they segment customers into long.21 on Thu. measured by the number of prior transac cant impact on repatronage. This finding is consistent with that ofrepatronage.6.jstor. Arnold.Although the preceding articles are unique. what are the optimal highlight reacquisition and follow-upt (after reacquisition) highly trained winback teams prices? and customer tems. However. segment customers on direct marketing firms the is recency. Griffin which lapsedand Lowenstein customers should the firm target for reacquis ( general outline for winning back tion? The second issue is lost critical for making cust offer decision practices from industry. 23 Nov 2017 16:02:55 UTC All use subject to http://about.. relating a customer's prior experience to repatronage inten Another common theme in the CRM literature is the tions and to the customer's desire to maintain the status quo degree of price sensitivity among loyal customers.. more generally. pur Unlike the research we have mentioned. counter to the mantra of they assert that notTargeting Decision all customers shou According to Griffin andapproach A popular Lowenstein. PreviousSpecifically.1 Although Reinartz and Kumar never actuallytomer behavior. experi- estimate price sensitivity. the majority of chase less frequently) are most likely to terminate their rel other CRM research does not address customer winback tionship with the firm. Consistent with with the firm compared with that of customers whose prior research. and Reynolds 2000). context.e. For lapsed or defected customers. Kannan. the consistent tomers actually pay a lower mean price than do short-life theme in the results is that previous experience affects cus customers. a widely held belief among direct marketer guide the targeting and offers made in the regain process. is positively associated with a higher likelihood o increase) does not. Using atomers strive to maintain the status quo. They determine that long-life cus. addition. Th was acquired affect SLTV estimates. which customers to target for repurchasing may hold in many cases. a few researchers have addressed pricing find that. our and (b) their subsequent tenure in a reinitiated relationship. decision to stay or to terminate the relationship or in term goods brands. They argue that inten pay higher prices (Reichheld and Sasser 1990). They explain this finding b choice than do price losses. Our research is distinct in that we model customer reacquisition and duration as a function of price. consumers' prior experience wit issues related to CRM. H : For restart customers. a decrease in price) has a signifi- with a product. customers who make fewer transactions (i. customers adapt to the new level of service provided by the switched-to 1 An inquiry with Reinartz and Kumar revealed that this result held even firm (Ganesh.175. firm for making targeting decisions in SLTV. a price tions. is that customers who have bought most recently and mor Using case analyses. it is important to TOWARD A THEORY OF RESTART CUSTOMER acknowledge that the relationship was terminated. Kannan. depends on prices. who show thatof whether repatronage is measured either in terms of the for customers who switch often among consumer packaged.e. by the two segments. but a price loss (i. and Raj (1992). Kalra. However. For exam rates and extends their insights into the domain of pricing ple. How does the amount of time elapsed since the about restart customer behavior: (1) the nature and influence last the of the prior relationship on customer reacquisition and purchase (or the length of the lapse) affect the chance of reacquisition subsequent relationship that evolves and (2) the responsive.org/terms . Schmittlein and Peterson (1994) find that in a brokerag strategies for customer winback. In when they accounted for basic differences in product categories. customers who have switched to a new firm after This content downloaded from 193. Recapturing Lost Customers 33 Building on the framework introduced ticularly relevant. Although weaknesses into deter this approach have defected. they that is. they als median split. It is noteworthy that this result holds regardless Krishnamurthi.belief is consistent with other research findings. and Bramlett (2000) Bolton. Boulding. Griffin and Lowenstein find that the often and have the highest monetary value are more likely t duration of a customer's lapse and the way that customer respond favorably to subsequent offers (Hughes 1996). they assert that prior experience drives cus- researchers have asserted that loyal customers are willing tomer to expectations and intentions. and Bramlett (2000) find that experience find that a price gain (i. Reinartz andtions are strongly related to the actual decision because cus Kumar (2000) test this assertion empirically. and the nature of the relationship that ma ensue? ness of restart customers to price. Assessments of SLTV and rationale for defection been identified. in the context of this research.

. respect toA the key exchange of payment premise of dissonance theory is that dissonance. to reduce the dissonance between their prior behavior (i. term effects of price on customer relationships. Logically. The specific combi- nation of prior prices and process by which internal refer- Offer Decision ence prices are formed remains an open issue (for a review. 1964). This can be con. show that On pay long-life customers the lower mean prices basis of this reasoning. ing. of customers based on relationship duration. Bolton(whichand Lemon (1999) use we refer to as Tenure 2 or second tenure). In contrast. the longer the time since the last purchase. Arnold. see Kalyanaram and Winer 1995). However.. increases in order to maintain equity in the relationship.. Disso. is because consistent with status quo bias. for service usage) to discussor consumers' lack ofuse of services. Applying this on the basis of weight of evidence. CRM and considers the long- Zeckhauser 1988). consumers seek to maintain pay- behavioral decisions and commitments). we argue that longer lapses may rep.g. we revisit the issue of prior experience. The reference price literature enables us to generalize that consumers use prior prices in the formation of reference H3: Longer lapse durations are positively associated with longer second tenures. Therefore. In the case of reacquired customers. than customers with shorter lapses.jstor. reinitiate a relationship after a long lapse results in a greater amount of dissonance relative to the decision to Although we derive H5 from the history of pricing research. This implies that cus. and usage contradicts both the long history in economics nance can vary in magnitude and is moderated by the of the negative effect of price on demand and the com- importance or intensity with which attitudes are held pelling empirical evidence across many disciplines. we believethan thatdo short-life the priorcustomers. responsiveness in erence for the current state or discrete inaction (Samuelson transactions. Thus. For example. H4: The reacquisition rate is higher if the price offered is lower. To understand further how price affects reacquisition and the lapse) and their decision to reengage in a relationship repatronage.175. the decision to H5: The second tenure is longer if the retention prices are lower. fit between two elements (e. 23 Nov 2017 16:02:55 UTC All use subject to http://about. and Reynolds 2000). the implied positive relationship between price customer's prior state (i. FEBRUARY 2004 having experienced another firm'sofservice exhibit supply and demand higher assert that higher prices lead to lower demand levels of loyalty and repeat patronage to the(e..34 JOURNAL OF MARKETING RESEARCH. Festinger 1957). research theirs was one of the first CRM suggests the following hypothesis: articles to demonstrate this unique result. a person attempts to engage in postdecision pro. Cohen (1960) we believe that it is important to test this hypothesis and asserts that the greater the amount of dissonance.ment equity gives rise in a service to pres- relationship and adjust usage lev- sures to eliminate or reduce the dissonance. Bolton and ceptualized as a drive to obtain consistency. attitudes Their research shows and thatbehaviors. Thus. Einhorn 1994). because customers with longer significant consideration to that assessment.e. antypically focuses on price exaggerated pref. prices and that reference prices have a significant impact on demand (Kalyanaram and Winer 1995). they will have longer subsequent relationshipssumer decision making. Specifically.6. Kalra. This general switched-to firm principle can be than do patrons of the firm who had directly never applied experienced to the reacquisition price offer. that economics is.e.They find that as customers gain confidence or experience cessing that reinforces the new decision that has been madewith a product. another provider (Ganesh. the lower is the statistical estimate of price sensitivity but on a median split likelihood of customer recapture. decision. the concept of we paymentreference equity (i. and Staelin (1999) show that customers give dif- To reduce or resolve the dissonance that occurs after a ferent weights to prior experience and current experience. the more likely a lapsed customer is Consistent to have withengaged economic theory. This behavior is lapses make stronger attempts to reinforce the reacquisition consistent with the existence of reference prices in con- decision. the either to reinforce the similarity between CRM and a stronger are the attempts to reduce it. it is worth acknowledging that this conclusion is not based on a H2: The greater the time since last purchase.org/terms . they weight their prior assessment of a given (Festinger 1957. For customer winback. following: resent more extreme attitudes. it might be expected that when restart cus- ship with the firm. dura. tionship with the firm creates dissonance relative to the However. Note that this hypothesis is still well We usefounded eventraditional caution in applying if the economic theory customer has not switched to a new to theprovider. thethe customer's percep- theory of cognitive dissonance (Festinger tion of fairness with 1957). the second tenure can be tomers assess their reinitiated relationship with the firm. Thus.e. els in response to price changes..21 on Thu. the decision to reinitiate a rela. a newReinartz and Kumar service or simply to have developed new (2000) behaviors. Because of To gain insight into the relationship between the long-term lapse perspective. inactivity) with the firm. we hypothesize the idea to our research.to price may be responsiveness tion and the duration of the reinitiated relationship more complex. The most basic question about the price offer decision is. evidence of the reacquired customer's degree of reinforce-they reflect on their prior relationship with the firm and give ment processing. How will restart consumers respond to price? General laws the logical reference point is the customer's prior relation- This content downloaded from 193. transaction-oriented business perspective or to highlight the tomers who have had longer lapses make stronger attempts unique perspective of CRM. (Eagly and Chaiken 1993.g. service more heavily than they do new information about the the current decision is the choice to reengage in a relation-service. Bould- with the firm. Lemon find that service usage levels may increase as price For any lapsed customer. reinitiate a relationship after a shorter lapse. price responsebecause of reacquired itcustomers. In this context.

because many of our hypotheses relate to second find that gains in price have a larger effect than do losses on tenure duration and because the data set we analyze lacks both the decision to stay in a relationship and the usage consistent decision intervals. such assess as price. face validity. these hypotheses suggest eling framework. Consistent withdiscrete Markov these models ar H4." in line with the statistics literature). in terms of stability. acquisition Thaler 1985). Second. and we defer to the empirical results. the data set includes many customers whose relationship with the firm exceeds the MODEL DEVELOPMENT period we observe. discrete and (2) the probability of entering a particular stateand predictive accuracy (Helsen and Schmittlein 1993). However.allowsZeithaml. Given the solid support for both sides of the issue. the Pareto/NBD. To in the subsequent period depends only on the current state. the last price paid before lapse (i. Similarly. are able to estimate LTV. so called because (1) time periods are least squares regressions.g. depends not only on their current state but also on their pur- chase history. Fifth. Morrison..e. thereby enabling a different effect with respect to price. Bolton and Lemon us to provide managerially useful insights about the second (1999) find that gains in price (i. our hypotheses for customer reacqui- refrain from making predictions about the impact of gains sition and duration differ. and are adaptable to all LTV. such as logistic and crete Markov chains. can incorporate covariates. so we must allow for censoring. for this purpose. another finding of the reference price literature is that Although we may lose some generality by not adapting an customers respond more to losses than gains (Kalyanaram and Winer 1995). The target customers for reacquisition and make the offer based Pareto/NPD allows for continuous rather than discrete time. see Jain and Singh 2002). price decreases) as it is for losses (e. but it does not explicitly model price or other decision vari- The assertion that customers respond to differences in ables as covariates. porating customer acquisition. and for ence to be either positive or negative.. decreases) have a larger lifetime. Thomas affect customer retention. 23 Nov 2017 16:02:55 UTC All use subject to http://about..175. Such approaches are drawing increasing interest we assert the following hypothesis: from researchers in the modeling of customer relationships. Of particular that differences between the interest. Given these requirements. Rust. and for customer retention. and Bramlett (2000) Third. Modeling Customer Relationships Bolton (1998) uses a hazard model in a CRM context to The growing CRM literature includes several modeling examine the relationship between customer satisfaction and approaches (for a review. Blattberg and Deighton 1996. Fourth." The most commonly used models are dis. Furthermore. Another CRM literature stream assumes that customers' H7: The difference between the current price last price paid probability before of purchasing lapse again (given (i. Bolton. assessments of value.org/terms .g. Lemon.21 on Thu. istics of our investigation in making our modeling choices. This implies that firms should customer cost information. 1985). increases). the models can be interpreted as incor- probability of reacquisition.6. we focus exclusively on the second lifetime (we term and Hogarth 1981.. we propose the for customer migration. new and Zeithaml price (2001) allow for thean influence how restartinvestigation customers of other decision variables. by This assertion is supported by asarguments modeling transition probabilities a function of covariates. Hazard models are well established in these articles model SLTV within the broader context of statistics..sp and Colgate (2001) show that price percept Bechwati 2001..g. we specify a hazard model. we select a continuous-time level. Reinartz that the price paid in the prior relationship anchors cus- and Kumar (2000) dichotomize the continuous probability tomers' perceptions and guides their subsequent behavior in predictions of the Pareto/NBD model and.customer Some of duration.e.e. we model price explicitly using covariates. on prices paid before the lapse. It is notable that this hypothesis Pfeifer and Carraway (2000) and Rust. Kahneman and Tversky 1979.e. Consistent with t 2001). are based on differences relative decision calculus.e.Usingwhich directly alternative approaches affect such as selection models or tinuity.distinguish our approach from the more common propor- This content downloaded from 193. Recapturing Lost Customers 35 ship Dwyer (1989) outlines alternative with the firm.. Kannan. CRM researchers have observed always-a-share model. If supported. Lemon (2000) generalize Dwyer's (1989) approach by Further drawing on reference incorporating both migration and price litera retention. price raises the question of whether their response is the Given this history.superior to other common methods. Schmittlein. two as distinct processes. price increases). and retention More simultaneously (Berger and Nasr. assuming an always-a-share sce- following: nario. which requires us to model the versus losses with respect to prices. hazard models have been customers ("always a share") instead of customers beingshown to be well suited for analysis of duration data and "lost for good. and Columbo (1987) H6 and H7 can have significant implications for the offer and and Schmittlein and Peterson (1994) use a stochastic mod- targeting decisions. researchers have explicitly modeled both to (e. Bolton 1998. that they do not current pr price in prior explicitly terminate relationship) their relationships withaffects negatively the firm) the second tenure. assuming a lost-for-good H6: The difference between the reacquisition p scenario. reacq customers minus last price in prior are relationship) identified before having developednegativ a relation- ship with the firm).. because our hypotheses relate to the impact on usage amount than do losses in price (i. When the initial share of the customer is zero (i. using individual the reinitiated relationship. Consistent with prospect theory (Einhorn First. our focused approach is necessary to address the four remaining characteristics. we focus on five important character- same for gains (e. This implicitly assumes that the firm can regain lapsedtypes of censoring. Thaler this "single spell. effects of price.jstor. we specification.

175. and 13 is the associated parameter vector.0). FEBRUARY 2004 tional hazards model (Cox time t 1972). and the duration component predicts the length of the sec. This approach Model Specification enables us to capture parsimoniously the effect of price on As we stated previously. thetical customer who is reacquired by the firm at time t as where a result of a reacquisition price offer. respectively. of the current duration (i. the stationarity assumption holds. CAIC and BIC are 1285 dummy var and 1279. As the subscripts oft and a customer is a "subspell. Note that the censoring value is known.. we partition the second tenuretively. 3We empiri The CAIC and BIC for this specification are 1289 and 1282. subspell si (si = 1. Probit specifica- The dependent variable is log-transformed to approximate tions have been used previously to model customer acquisi- more closely the normality assumption about the residuals. the duration of the subspell is right censored. xisi is the customer's vector of predictors chastic component. Si) as a conditional regression with the Our split hazard specification comprises separate reacquisi. Recogniz- ing this relationship. Although this occurs relatively infrequently model this linkage. . p. The reacquisition component measures the probability of recapturing a lapsed customer.X0). We est For the specification without the dummy variable.. This customer's to duration consists it as of two hazard model" (it may also subspells: be termed one of length a "censored 81 (which is right censored) that is model"). respectively.e. customer-specific preferences for reacquisition and tenure consists of one or more subspells that differ only duration in are not fixed. we must specifying variance components. it is observed). and y is the associated parameter vector.2 To illustrate. In this way.jstor. during subspell si. from the aut This content downloaded from 193.sii3 is the deterministic component. we refer + 81 + 82. We explicitly relationship. Given the likely relationship between the customer's Modeling of the second tenure is somewhat complicated acquisition and retention behavior (Thomas 2001).6. and then terminates the second tenure at 2We tested whether there were systematic differences between customers a with a single subspell and customers with multiple subspells by estimating a more general specification of our model with a dummy variable that cap- tured single versus multiple subspell customers as a predictor of duration. tion.org/terms . associated with the reacquisition price and one of length 82 that is associated with the second price. in which case it is also right censored. If the customer terminates the relationship before component as a latent variable probit with observation the price changes. we allow for heterogeneity across cus- implies that the duration of a subspell does not depend on tomers. Moreover.. 23 Nov 2017 16:02:55 UTC All use subject to http://about. Moreover. 36 JOURNAL OF MARKETING RESEARCH. wi is the customer's vector of predictors. The observed duration may also be limited by the observation (1) Z horizon. Thomas 2001). Using this For the reacquisition and duration components. given that the firm successfully recaptures the customer. by (see the data description in the following section). so ti and ai represent customer-specific preferences. pp. respectively. it is a necessary condition to esti- mate this model (Amemiya 1985. we allow the distributions of customer- the length of prior subspells. We specify errors of the nevertheless allow for price changes to affect the customer's reacquisition and duration components. We conclude that there is no evidence of systematic in duration differences between the durations of customers with single and multiple 4Details of subspells. as probability of terminating the relationship. We note that follows: Amemiya (1985. along with customer heterogeneity. is offered a second price at time t + 81. following observation equation: tion and duration components. 363).3 starts when the customer is reacquired by the firm and ends We model the duration component for customer i during when the customer terminates the subsequent relationship. they are distributed across house- the offer price. is the sto- chastic component. Eisi is the sto- where wiNy is the deterministic component.. 433-35) shows that a split hazard model of the form that we specify is simply a generalization (5) rh of a single spell of a continuous Markov model.4 tion (Hansotia and Wang 1997. or length of time that a given price was For customer i (i = 1. consider a hypo- specific preferences to be correlated so that BVN(0. respec- assumption of stationarity. and that each period during which a given price is offered to the vi and Eisi are random errors. we focus on a single spell that second tenure duration. each customer's second indicate. the censoring value. This approach to linking acquisition and retention where yrsi is the latent duration of the relationship and cisi is explicitly incorporates left censoring (Thomas 2001). Other- equation wise. we specify the reacquisition offered. C). we adopt the continuous Markov (6) Eisi process assumption that the probability of the customer ter- minating the relationship at any point in time is independent where N(04) and N(0. We specify the We model the latent dependent variable zi* with the linear latent duration of subspell si of customer i as model (4) ln(yrsi) = Xisi i3 + cisc (2) z where x." Thus. it is stationary).21 on Thu. (3) y ond tenure.e.. then yIsi (i. it is by the firm's propensity to change the offer price during the important that these components be linked.

we allowoffers from the firm at any time before ourprefer a customer's observation relationship with theperiod. Gelfand and Smith 1990. firm Thus.00 Duration of lapse (in periods) 10. Allowing for correlation response to such a sequence of between offers. The reacquisi- unlike some other contractual selling agreem tion component of the data includes a single observation for tions are nonbinding..e. the number of periods elapsed since the cus- days (see Table 2).12 $. successful or failed reac- period. ourmore received multiple price offers. so none had received reacquisition The first and most obvious variable included in the esti- mation is price.25) Average retention price decreasea $..175. Note that the firm customer durations are right censored.75 279. Thus.97 684-1 229.org/terms . single price for reacquisition but may be offered multiple Table 2 DESCRIPTIVE STATISTICS Total Sample Successfully Reacquired Sample Standard Standard Mean Deviation Range Mean Deviation Range Reacquisition price offer $2.05 34-1 5. that is.8% terminated company is roughly one month). Of the customers who re tomer's most recent purchase (each period as defined by the tionships with the firm.43 $. 416 were successfully reacquired. error terms More specifically.25-$.42 217. see Chib 1993).00-$1.75 Last price paid in prior relationship $2.62 30-1 Prior tenure (in days) 179.) All the customers examined in this analy newspaper seven days a week. we present the averages over the duration of the reinitiated relationship. the firm does not engage in price disco customers targeted for reacquisition (i. the price of the last pur- during the two-year observation horizon.00 Average retention price increasea $. First. available (Casella andalthough most George 1992. the duration and we conjecture of aboutthat their ship.se tomers have which single stochastic multiple subspells.92 684-2 aBecause the price is time varying.75 $2.03 4.00-$1.21 on Thu. Recall that each subspell represents a different price offer from the firm during a given customer's second tenure. In summary. Recapturing Lost Customers 37 In this way.00-$1. T chase. customers who did not respond did Model Variables not receive multiple offers).00-$1.jstor. cus for the discrete and Observations continuous for the duration component component differ from reacquisition observations ard specification is similar in in two ways.41 $1.47 $3. The (9) Si The second difference simulation-based methods of estimating is thatdistribu- posterior the price in ea characteristic tions of parameters in censored of that data and missing subspell and so may problems have only recently become reacquisition price. reacquired.30 $1. and the length of the first tenure.15-($1.e.00-$1.15-($1. This content downloaded from 193. C = 566). therefore. they commit to a w Data remains fixed for a given period (roughly were unable to determine from the data wheth The data we used to estimate the model come from a precommits to buy for several consecutive p newspaper subscription database and comprise 566 lapsed less. Thus: (8) Var(Eis) We follow Ainslie and Rossi (1998) in estimating our variance components specification in a Bayesian framework by using Markov chain Monte Carlo methods.error 140 received multiple vari 2 and 4 are price offers during the observation period (an average of 2.75 Average retention price offera $2.51 11.6.e. The average length of the second quisition).75 $2. each customer in the data set lapsed only once. customers each lapsed customer that consists of the reacquisition price continue or terminate the subscription at an offered..32 $.44 $3.44 $3. spirit tosome acus. When cust DATA AND MODEL VARIABLES receive the newspaper.5 Of the chase commitments of more than one perio customers. 66. 23 Nov 2017 16:02:55 UTC All use subject to http://about. observation period (i. tomers forpaid a single price application to(the reacquisition censored out their relationship regressions.17 $.25) $.38 $.05 684-7 Observed restart relationship tenure (in days) 177.00 282.75 Reacquisition price difference $. the current price offered/paid in the reinitiated 5We removed customers who lapsed or defected as a result of relocation relationship (recall that customers are offered a or vacation from the data.46 $3.32 $1.10 $. (A complete discussion of with the firm. Desc made only one reacquisition offer per customer during our are provided in Table 2. estimation procedure is available as a technical report on request. for of the th 416 customers that werethe are correlated.19 price offers for customers who received multiple (7) Var(rii prices).15-$.28 5. our application to does be not include correlatsequential offers to tomer's preference for lapsed customers. Moreover.22 $.47 $3. for a total of 582 subspells. the result of that offer (i.48 $1.10 $.

6860 considered two alternative approaches to modeling price dif- (1) ferences. the absolute effect of price Covariate Effects on the Reacquisition Probability is much more important than the effect of price relative to Consistent with Hia and H2.0473 observed by the customer.78) price differences enables us to assess asymmetric response Tenure 1 . How- parsimony. Thus. Table 3 reports posterior means of parameter estimates literature. Lapse duration meas- ures the number of periods elapsed since the customer's last B purchase.97) Lapse duration -. p.e. The first approach is to have (1) a single variable. the duration elasticity of price has a H6: The likelihood of a customer being reacquired decreases higher magnitude than other predictors. CAIC and BIC are 1288 and 1281. hood. we find that it is consistent with the assertion that loyal customers are willing to pay higher prices (Reichheld 6For the model specification with price decrease and price increase vari- 1996) but contradicts Reinartz and Kumar's (2000) finding ables. Reinartz and Kumar (2000.. Consistent with economic theory and prior H4. price increase is the dollar al3 is less than or greater than zero. For the specification that long-life customers pay lower average prices than do with only price difference.. relationship are not likely to be effective.526 -. "we expect This content downloaded from 193. the elasticities indicate that were increases relative to the last price paid in the prior the offer price has the largest effect on reacquisition likeli- relationship.org/terms . The data show for the reacquisition model as well as posterior probabilities that 26.jstor. (. This result implies reacquisition and the length of the second tenure. Comparing this to the other relevant CRM ship. regardless of the price that the customer As we noted previously.175. tion that customers make decisions about reinitiating the we find that higher retention prices lead to longer relation- relationship based on comparisons with the lapsed relation- ship durations. prior relationship.21 on Thu. ever.047 -. price difference = current Impact on Relationship Duration Price 1.9000 which we suggest is a logical reference for the customer. COVARIATE IMPACT tionship with the firm before lapsing. Specifically. This is an impor- shows that the probability of a firm reacquiring a customer tant insight for managers because it suggests that reacquisi- is higher if the lapse duration is shorter and/or if the first tion strategies that emphasize decreasing price relative to the tenure is longer. 38 JOURNAL OF MARKETING RESEARCH. which is the difference Price difference -. However.7% of the prices paid or offered In terms of relative impact.784 . and we specified the preferred approach on the Tenure 1 .91) rent price paid or offered (i.194 1.1802 and price increase (i. An impor- that pricing in the prior relationship anchors response totantthedifference is the sign of the price effect. a loss) variables. Tenure 1 and lapse duration also have a material influ- RESULTS ence on the reacquisition outcome. we estimated alternative specifi- was accustomed to paying before the lapse. 28) state. 23 Nov 2017 16:02:55 UTC All use subject to http://about..1936 price . FEBRUARY 2004 Table Tenure prices over the duration of the second tenure). A more fruit- the results also show that customers are more likely toful beapproach to winning back lapsed customers is simply to reacquired if the reacquisition price is lower.e.312 -. Comparing the corrected should not be enticed with significantly lower prices. the reacquisition model the last price paid in the prior relationship. one with the price difference variable only and implies one that customers who previously paid low prices which separated gains and losses. offer a low price. Notably. Akaike information criterion (CAIC) and the Bayesian information criterion (BIC) for the two specifications. This also cations. we (1) define price decrease as the dollar amount of price decrease Price increase -. The results support reacquisition decision.6. we report parameterthan or greater than zero) for the duration equation. Thus. price difference has a much smaller effect.686 -.6 Thus. a gain) (1) Price decrease 1. amount of the price increase relative to the last price the firm offered the customer. there are with the difference between the reacquisition price and several the notable differences between the factors that affect last price offered in the prior relationship. As in the estimates from the former specification.76) before the relationship lapsed. respectively.4539 to gains and losses by defining price decrease (i. Consistent with reacquisition offer. The 3 1 variable measures the total duration of the customer's rela.reference price). note that both variables are coded as positive values.556 .6% of the prices paid or offered in the restart rela- (in parentheses) that the parameter is less than or greater tionship were decreases relative to the last price paid in the than zero.0526 between the last price in the prior relationship and the cur. Price -.454 . the second specification represents a better balance of fitshort-life and customers (in a catalog retailing context).900 -.e. Variable (Posterior Probability)a Elasticity A fourth variable measures the difference in price with Impact on Customer Reacquisition respect to the last price paid before the relationship lapsed. price difference. The second approach to modeling (. depending on the sign of the posterior mean. respectively. and 34.0523 relative to the last price the customer was offered by the firm (. this supports the asser- Bolton and Lemon (1999) and contrary to economic theory. Covariate we Effects on Length of the Second Tenure find that the model specification with price difference wasTable 3 also reports posterior means for parameters (and preferred to the specification with separate price increase associated posterior probabilities that parameters are less and price decrease variables. CAIC and BIC are 1285 and 1279. In interpreting the results. More generally.7843 basis of model selection tests. We (. A positive value for price difference (1) means that the current offer price is higher than the last price Lapse duration -.

elimination of (1) we find all first tenures that less than ten days." erogeneity and correlation between customers' intrinsic Bolton and Lemon preference (1999) explain to be reacquired this and for their intrinsic preferenceeff payment equity. the results do not ing decisions for restart customers is complex.309). FORECASTING SLTV sion processing can explain the effect of price comparisons.05 in the full the data set become nonsignificant. the length of the second tenure appears to be unaffected.21 on Thu. suggesting that there is no relationship between the parameter estimates suggest that the last price in the prior the length of the lapse and the customer's second tenure. we found no sign Specifically.789 .05 (actual p-value = .8 Thus. mates revealHowever. Specifically.5_andi 5_ -.09. we between lapse duration and the incorporation of customers' explore how the prior price affects the profitability of restart preference heterogeneity. Using a NPV of the profits generated after a customer is reacquired. although firms are less likely to assuming specific marketing costs.jstor. which suggests increases and price that the likelihood of the customer decreases in the being reacquired reacqu is they made this distinction after inversely related to the likelihood the of the customer relat remaining reinitiated. price increases sets.e. The esti- in reservation prices. become significant. Anto alternative explanation maintain the relationship after reacquisition. was significant at a = . or In addition.9 have been reacquired. (2) all the decreases on the second tenure second tenures less than ten days. We used estimates from the reacquisition and tenure.. If unmodeled individual charac. a relationship prior customers who rel the reinitiated relationship. we allow for customer het- industries. the positive The descriptive data in Table impact 2 reveal some short first ofand g decreases) on secondsecond tenure observations. The difference is that the expected SLTV takes into account the reacquisition profit or loss 7We thank an anonymous reviewer for pointing out the possibility that and discounts the post-reacquisition LTV by the probability of reacquiring our heterogeneity specification might mask this relationship.. we determined the reacquire customers who have had longer lapses.10 in the full data set.? In summary. teristics. Although Festinger's (1957.041) in the second reduced data set (i. of who In other words. tomers in terms of retention. customers H7. any relationship between the lapse and the second duration models to predict the likelihood of a firm reacquir- tenure would be obscured by the specification of preference ing and retaining a customer with certain characteristics. Bothmay be lowerpayment equity an in the reinitiated relationship..parameter knowledge estimate for the duration about model is consistenthowwith efficiently.asy to gains and losses points to ter estimates from using the a notable full data beh set.e. eliminating all Another issue in our investigation is the link between second tenures of less than ten days). Itposterior is als probability that 2. are easiest to win back) may not Consistent always be the best cus- research (Bolton. price in none of the three reduced data sets did are decreases) the customer's decisionany parameterto estimatereestablish a re that had been statistically significant have a noticeable effect. In this section. the results suggest changes in any parameter estimate in thethat three reduced whe data (i.may be Th highlights the importance more inclined to restart of the(i. Recapturing Lost Customers 39 these factors to have differential variance components impa approach. that customers have a negative our bias towardmo allows for different reference reacquisition (posterior mean of i = -1. they are positively inclined referen to continue the relationship reject this alternative (posterior mean of a = 1. 1964) assertion are robust to the inclusion that or exclusion of unusually short p postdecision processing tenures. 23 Nov 2017 16:02:55 UTC All use subject to http://about. customers and the optimal pricing strategy of the firm. that reinforces th have made. This content downloaded from 193. 95% explanation. is statistical and (3) all first and sec- the effect of price increases is Compared ond tenures less than ten days.6. were should be based on the expected profitability of a reacquired correlated with the lengths of both the lapse and the second customer. Furthermore. at a = . Lemon's but when they have ( the presence of heterogeneous been reacquired.prices 95% posterior a Because replicate we Bolton probability that -2. not. However.743. when they expected SLTV of a potentially reacquired customer. which Link Between Reacquisition and Length of the Second Tenure was significant at a = . The asymmetric impact of price increases and decreases in it does not explain our results about the effect of lapse dura. Kannan. the customer. Specifically. 91t is important to note that we computed expected SLTV and not the reacquisition and duration of the second tenure. This positive contexts that price sensitivity decreases intercept w product familiarity. a firm's targeting decision and offer decision tial behavior (Bawa 1990) in newspaper subscription. or bias in favor our previous of conjecture that the a customer's status price sensitivity q repeat purchases. By heterogeneity. conjunction with the current price effect suggests that pric- tion on the second tenure.org/terms . with This our parame. 8The price difference parameter for the reacquisition equation. support H3. which is in thein support relationship. Ultimately. we estimated our model with impact three reduced data sets: of increases).592.094). and in cus fected by deviations only one that do case did a parameter that not had not been suppor significant reestablish the relationship. To tenure assess the robustness of ourhas a duration tude than does the negative results.This behavior we suggest that our inferences Festinger's (1957.175. such as a propensity toward variety seeking or iner. The posterior sensitivity are plausible mean of the correlation between the explanations in two ou Although customers did preferences not (estimated using adistinguish is is -. 1964) theory about postdeci. It relationship affects a customer's price sensitivity and behav- is possible that this null result is due to the relationship ior in both reacquisition and retention.and Bramlett Lemon 1999).e.

share are not maximized with we provide highlights of a numerical simulation in Table 5.75 to $3. For the average and modal cus- ever. even retention prices. because mization but rather employ heuristics to set their prices.80 greater than the last the firm can use to distinguish customer reacquisition targets price. in which the average reacquisi- tion price was $. In our data.80. A class of heuristic approaches that the firm can use is cost based: pricing at cost ($1. theand logic of considering these reacquisition pricing strategies might be questioned. this pricing strategy.00. Firms that target this type of price through these three levels. However. In the likelihood of reacquiring a customer is .01.jstor.175. we fixed all covariates at their averages and modes. As with the pure optimization The values reported in Table 5 are the expected SLTVs of approach.56. However. offers ($1.49. the firm knew three and characteristics of lapsed customers: (1) the associated profit will duration ofactually theiroccur.20) and maintaining this practice. on average. Firms may be tant to acknowledge that firms may not focus on price opti- tempted to choose $2. In At the extreme. or equal to the strategies for the reacquisition and retention of lapsed cus- last price paid before lapse. loRelaxation of the time-invariant costs assumption is a trivial exercise because our demand functions are not a function of costs. This price is two stan- the reduced duration of the second tenure.6. we assess optimal pricing strategies in terms of shows that reinstating a customer at the same price as the SLTV and evaluate heuristics that may be observed in last price paid before lapse ($2. dicted the expected SLTV for various customer types.reacquisition. 40 JOURNAL OF MARKETING RESEARCH. the firm may price low enough so that the probability of theory. price above the last price in the first tenure results in the Offer Decision highest SLTV.66 and the expected SLTV is costs. or even positively. Logically. In our numerical analysis.21 on Thu.org/terms . (2) the length of their first tenure reacquisition price is $. The predictions reveal that. this is a profitable customer and one the firm should reacquisition is nearly one. this customer's expected ability that is virtually one. the price decrease.00). price is suboptimal from a profitability perspective.677.30 and then increasing the and implements a profitable reacquisition strategy.20. Price changes of this magnitude rarely occurred in who are likely to be profitable from targets who are not. (3) the last price they paid. as is shown in Table 4. correlated respectively. respectively. $27. the reac- individual-level cost information. This is important because it suggests that customer ." it is uncertain whether the anticipated customer response We assumed that before reacquisition. the average increase three factors that are known before reacquisition.30. for a prospective target. its are not always strongly.890 to .30.75 and then raise the retention prices that are lower than the last price paid before lapse.00) or SLTV of a customer whose profile reflects the tenth per- centile (from the data) of each of the below three costfactors (we used $.80. note that the second To assess how the offer decision affects expected tenure duration and marketSLTV. 23 Nov 2017 16:02:55 UTC All use subject to http://about.50) is for $.10 less than the last price paid before lapse. Region A in Table 5 shows some of the possible pricing combinations that are consistent with this strategy. and the results might vary. ing all other predictors at their median values except the and if the retention price was increased. it is important to acknowledge that duration and prof- tomers. The analysis shows Pricing that relative the to expected costs. we pre- was $. and less than the last price in the prior relationship. The theoretically optimalwith lapse. below.20 as the reacquisition price. If the reacquisition median levels and found that the model suggests a reacqui- costs increase even slightly. the result is that the firm should offer First. we fixed all vari- though second tenure duration is not maximized. If we had At a fixed price of $1. Table 4 also shows the expected SLTV of reacquiring of thea average customer. values and assumed that the costs are fixed over time. Profits Optimal pricing strategy. if the firm's tendency is to offer restart customers a reacquisition price of $1. price to $3. it is impor- the last price paid before lapse is $2. When conducting this type of analysis. FEBRUARY 2004 Targeting Decision Note that whereas this strategy is theoretically "optimal. Table 6 highlights some of the calculations at a reacquisition price of $.998. we find that implementing a heuristic approach in customers for different reacquisition prices and the average which prices increase over time maximizes profits.10 This Another class of heuristics that can guide pricing strategies analysis addresses several important issues about pricing for restart customers is pricing above. As the firm lowers the reacquisition itable for the firm to pursue. ables that characterize the prior relationship at their median Pricing relative to the last price paid before lapse. This strategy results in an acquisition likeli- the most profitable approach is to offer a low reacquisition hood of approximately . the (Reinartz and Kumar 2000). the median value of tomers. dard deviations below the mean of the last price before lapse.985 to ment. Our analysis this section. Given that our estimation results reveal that the second winback should be a selective process and that not all lapsed tenure duration is negatively correlated with the likelihood customers should be pursued. This content downloaded from 193. To generate a reacquisition prob- attempt to reacquire. the customer becomes unprof- sition price of $. the likelihood customer must carefully manage their reacquisition invest- of reacquiring a customer increases from . we fixed the covariates at their profit is sensitive to reacquisition costs.45 the firm. Our analysis shows that lower- firm targets attractive prospects among its lapsed customers ing the reacquisition price to $. Fix- the data. the most profitable offer is a reacquisition increased margin from the retention price compensates for price and a retention price of $1. Note that this strategy does not price and a low retention price. If we limit the price maximize the length of the second tenure and thus does not decrease to be within two standard deviations of the mean maximize the firm's long-term market share. these are variables that and the optimal retention price is $. Again. we could make demand a functionquisition of likelihood is .17. How- modal customers of the firm. If the optimal strategy is can be improved if the firm follows one of two pricing explored within the range of prices that the firm typically strategies.

0 $61.45 Covarites ValueofA Observal 90thPercnil 2 .Recapturing Lost Customers 41 4 1 .01 1 5 35 38 $2.89 $28. $2.74 $.0 $2.35 $2.0 $1.jstor.01 $.07 $.43 $(.869 91 13 $.65 $.9 $.968 7 $.01 $(.7 $40.75 $1. $1.9 $20.43 $24.19 $4.07 Averag Customer Reacquird 1 .8 $2.0 $45.75 365 $1.175.75 $1.5 $2.0 $51.4 Customer Reacquird 5 6 .68 $1.7 $4.6.847 5 192 15 $2.90 $1.0 $7.0 $4.83 $59.org/terms .43 213 $1.86 Covarites ValueofA Observal 75thPercnil 6 .62 $2.0 $36.43 $.0 $.Whxv Profiles Reacquiston Retnio This content downloaded from 193.38 $5.83 $67. 23 Nov 2017 16:02:55 UTC All use subject to http://about.09 $38.7 $2.75 $1.59 $29.32) $1.146 3 17 50 103 $2.43 $.75 $1.0 $2.43 $1.3 Covarites ValueofA Observal TARGEINCUSOMPFL 25thPercnil .0 $1.68 $1.8 $41.21 on Thu.mb.43 $1.43 $1.68 $2.0 $29.47) Covarites ValueofA Observal 10thPercnil Reacquistonpr Lastpricenolh Lapsedurtion() Tenur1(days) Probailtyfecqusn Reacquiston Expectdraquisonmg Averagtniopcd Pricehang PredictTnu2(ays) Periodtncs Expectdrniomagvqus ExpectdRaquisonVl PredictTnu2(pos) Expectdrniomag Notes:Fracquindpfl.0 $1.05 178 29 $2.0 Modal $32.0 $2.0 $6.23 $1. $2.53 4 17 127 $2. $2. $1.79 Covarites ValueofA Observal 50thPercnil Table4 .38 $1.

9 19.175.0 28.6 25.80 25.3 24.9 16.14 21.75 20.75 29.45 36.79 23.2 28.95 21.3 $47.85 2.0 2.6.69 26.1 $38.95 2. 26.14 21.90 $2.81 23.6 34.47 18.27 18.6 29.2 42.3 23.15 51. 27.72 19.6 $35.71 25.5 30.29 3.53 23.6 18. FEBRUARY 2004 $3.41 2.84 RegionA 19.35 34.5 38.95 3.9 25.4 18.4 $3.47 17.51 $4.5 17.9 36.05 3.28 25.8 34.62 18. 26.56 19.75 36.1 27.1 34.63 21.68 28.8 23.64 2.6 32.37 $40.81 23.23 16.0 17.49 32.87 26.51 2.5 19.69 17.94 31.36 23.9 21.18 24.41 25.47 $42.50 23. 28.4 24.97 20.01 24.5 23.75 2.35 17.45 2.31 24.8 31.37 27.4 $1.4 17.8 15.84 30.62 25.76 15.97 2.60 32.80 2.57 21.6 24.8 23.6 24.63 28.85 1.1 25.74 20.01 25.15 31.83 19.16 23.1 27.0 18.15 Reacquiston Price $.70 24.85 45. 3.62 48.5 30. 2.35 23.79 31.8 19.3 23.04 RetnioPrc 19.35 $2.54 $31.16 24.10 $49.36 28.21 32.48 $3.1 21.48 $2.8 23.84 25.8 $1.17 21.67 27.6 31.5 23.49 20.6 $2.78 2.67 18.61 36.4 20.74 25.75 1.70 21.15 2.81 25.03 21. 28.15 34.70 3.5 26.15 32.04 2.41 19.5 2.02 18.87 25.79 Averag Table5 RegionB EXPCTDSLV 19.5 $32.95 47.8 21.03 25.5 25.58 30.81 29.07 21.57 21.65 2.49 17.0 $2.97 2.85 35. 20.26 $2.5 20.9 $2.4 28.9 2.3 17.89 23.92 34.61 26.3 15.8 17.78 21.8 3.60 32.15 $30.6 26.65 40.95 34.6 26.21 on Thu.97 20.42 30.05 32.10 2.73 20.65 28.7 18.17 34.6 24.38 4.5 19.08 25.67 31.6 20.9 23.84 19.38 20.6 19.75 2.92 30.74 2.48 16.0 18.0 30.58 15.7 23.19 $2.0 24.4 $2.79 24.04 15.73 $36.30 21. 37.47 18.7 16.8 19.71 23.57 17.52 16.87 2.85 26.0 2.93 27.35 2.01 2.59 2.85 17. 18.52 37.01 26.7 $2.10 2.9 19.6 17.6 20.95 21.87 $51.05 49.91 27. 29. $34.5 21.0 40.38 16.1 24.81 24.59 35.05 2.34 18.50 1.98 2.50 18.49 36.46 26.85 20.9 29.5 2.9 27.75 25.20 30.9 16.jstor.0 21.31 26.4 2.06 16.8 20.35 27.0 19.3 20.36 28.0 29.3 $31.39 25.5 23.81 2.6 27.5 31.82 38.8 20.30 This content downloaded from 193.76 24.94 31.0 29.8 26.8 17.5 19.98 32.81 .90 17.73 21.20 $2. $1.2 38.76 18.28 32.1 31. 23 Nov 2017 16:02:55 UTC All use subject to http://about.47 20.36 26.84 26.2 16.96 27.1 31.32 17.04 16.84 21.0 1.87 3.75 43.42 JOURNAL OF MARKETING RESEARCH.91 23.org/terms .0 24.6 24.74 23.78 24.41 $3.1 2.51 46.80 2.39 23.78 19.

However.582 2.02 $31.90 .998 . the effect of price increase relative to prior price on relationship tenure.998 . lapse duration.20 $ .50 . Specifically.81 $33.95 .20.80 $ 1.e.80 .20 and significantly 1.30 $ .11 To increase profits by price decrease on length of the second tenure.48 Expected retention margin $35.20.65 .416 prices.35 .37 Expected Reacquisition Value $35.05 $ .20) $ .20 $ 2.05 $42.21 on Thu. it might be concluded that the key to 2.389 11 It is notable that when we computed expected profits for price increase Notes: We calculated all probabilities at the median values of the prior strategies.85 . able when reacquisition and retention prices are both $2.30 .16 $53.00 .00 Expected reacquisition margin $ .25 Absolute price change $ (.57 There are two key factors that increase the expected Second. The key to a firm's successful implementation of a price increase strategy is managing the trade-off between a lower Table 7 acquisition rate (due to higher reacquisition prices) and CUSTOMER REACQUISITION RATES increased margins (due to higher retention prices).00 $ 1.30 $ .75 .677 1.649 higher than the retention price will result in an expected 1.60 .595 Summary of Numerical Simulation 2.75 $ 2. and last prior price variables.00 $ 1.25 .20 $ 2.30 $ .20 $ .00 $ 1. using this strategy. Recapturing Lost Customers 43 Table 6 EXAMPLE OF SLTV CALCULATION Profiles Variations in Retention Price Reacquisition Reacquisition price $ .20. 23 Nov 2017 16:02:55 UTC All use subject to http://about. Because of this trade-off.40 .20 Retention Average retention price per period $ 1.66 $48.398 3.175.476 performed our simulation analysis by assuming a moder- 2. firms may opt to increase cantly higher reacquisition rate.00 $ 1.05 .20 Lapse duration (periods) 6 6 6 6 6 6 6 Tenure 1 (days) 117 117 117 117 117 117 117 Probability of reacquisition .00 $ 1. The increased duration compensates for lapse.10 .00 $ 1.20 $ .00 $ 1.30 $ .85 .663 quisition price that is greater than $2.445 have been recaptured.455 relationship characteristics). Our analysis shows that the Table 7 shows how the reacquisition rates vary with the firm can moderately reduce the reacquisition rate (see Table reacquisition prices.00 $ 3.75 $ 3.20 $ 2.30 $ .80 .17 $42.435 recoup the losses from reacquisition by charging higher 2.570 From these results.00 $1. at the median value of the prior 2.00 $2.27 $53. relative to a price of $2.70 .466 ately attractive profile (i. This approach maximizes margins but not long-term 2.53 $37.00 $ 1.58 $48.998 .998 .22 $31.05 Predicted Tenure 2 (days) 178 142 118 123 128 131 134 Retention costs $ 1. their behavior is such that the firm can 2.20 fixed price.20. When attractive customers 2.20 .97 $42. duration was small (the effect of price decrease was irrelevant).00 $ 1. Region B of Table 5 shows some of the price combi- the lower retention margin that is received when the reten.55 $ .07 $53.org/terms .998 .425 2.635 SLTV below the expected SLTV attainable at a fixed price 1.30 Last price in prior relationship $ 2. A reac- $1.6.45 .20 $ .521 has revealed that the firm may not want to price so as to 2.545 2. The first is the signifi.33 $36.15 .30 $ .608 2.20 $ 2.20 $ .998 Reacquisition costs $ 1.533 customer reacquisition. Note that we 2.55 .20.622 of $2.95 . restart customer lapsing again. The second factor is the impact of the 7) and still increase expected profits.998 . our targeting discussion 2.30 $ ..75 .jstor.00 $ 1.20 $ 2. nations for which expected SLTV exceeds the SLTV obtain- tion price is less than $2. there are limits on how high the firm can set the reacquisition price relative to the retention price and Reacquisition Price Reacquisition Probability generate profits beyond those of a $2. to hedge against the risk and potential costs of a SLTV with the low-price strategy.20 $ .09 $31.487 2.50 $ 2.00 Expected retention margin given reacquisition $35.510 reacquire all lapsed customers and instead may want to 2.20 $ 2.39 $37. This content downloaded from 193. 2.498 focus on customers with attractive profiles.00 .68 $33. the firm must increase both the reacqui- the length of Tenure 2 increases when the reacquisition price sition and the retention prices above the last price before is less than $2.25 $ 2.407 2.78 $48.00 $ 1.557 managing customer winback most profitably is successful 2. prices above their prior levels.61 $33.90 .45) $ (.

Cambridg maximize customers' SLTV. Paul D. and thus actual profit-maximizing ing share is to implement the heuristic of lowering pricing prices strategies may vary. areas that need further exploration.175. last price paid during the first tenure plays a role throughout Chib. (1960). a 100% retention rate is seldom feasi- be explored using a game theoretic analysis. and John Deighton (1996). Bawa. 74 In addition. Furthermore. customers who are Bolton. in our application. "Bayes Inference in the Tobit Censored the winback process. Throughout the relationship. (1998). David R. "A Dynamic Model of to deviations in price relative to the last price paid before Customers' Usage of Services: Usage as an Antecedent and Con- lapse. At the point of reacquisition. 136-44. 37 tomers respond in a way that reinforces their decision to (May).org/terms . F. and Nada I. The Psychology of Atti- winback programs. Robert (1989). At the time of reacquisition. George and Edward I. To do this. However. Bramlett (2000). expenditures. In this context. 46 (August). is an important insight for firms because it shows that the 167-74. 463-84. Price endogeneity might retention. 9 (3 263-78. "Modeling Inertia and Variety Seeking Ten Firms' significant lowering of reacquisition prices to dencies in Brand Choice Behavior. Marketing Science. Takeshi (1985). 28 (1). sequence of Satisfaction. sistent with this outcome." Marketing Science. increase the likelihood of reacquisition is an optimal strat- Berger. and price decreases rel- Casella. Robert C. However. Ideally." for Customer Retention and Value. To maximize share. such as HoneyBaked (as we mentioned Einhorn. A firm that sends fixed-value coupons to tudes. level remarketing efforts and marketing cost data might Dwyer. Gary Getz." Journal of Direct Marketing. able or profitable. Customer ship. "Implica- negative correlation between a customer's preference for tions of Loyalty Program Membership and Service Experiences reacquisition and their intrinsic "retainability. 18 (4). with second tenure duration. and Matthew D. 49-61. 11 from exploring this." Journal of the Academy of Customers also demonstrate a dynamic response to rela. William. and Richard Staelin (1999). dynamics of the baseline hazard could be studied. Alice H. all lapsed customers. Nasr-Bechwati (2001)." Marketing Science. the customer is sensitive to Equity: Building and Managing Relationships as Valuable Assets. P. Although this research highlights the importance of Cohen. 45-67. "The Quality Double Whammy. 6-13. 1 For the relationships that are attractive to reestablish. (1972). firms need to employ profitable winback strategies that Amemiya. to defect rapidly. particularly when it requires setting a low Such an investigation would improve our understanding of retention price." Journal of Marketing Research. Orlando. In other words. Lemon (1999). "Optimal Nonuniform Pricing with in the first section). (1994). FEBRUARY 2004 market share. Advanced Econometrics. relative to the last price before theAlso lapse. response to price varies at different phases of the relation. MA: Harvard University Press. only a mature or long-life customers and consequently emphasized single reacquisition offer is made. however. "Customer Lifetime Valuation to Support affect our conclusions. Our analysis provides the additional insight that 100% given a data set in which the firm makes many price changes retention (or other high retention rates) is not always desir- over time. Ruth N. the absolute price. In addition. (2)." Marketing Science. 23 Nov 2017 16:02:55 UTC All use subject to http://about. This content downloaded from 193.21 on Thu. Cox. customers respond negatively to price." Jour- nal of the Royal Statistical Society. Kapil (1990). Behavior Across Product Categories. and Shelly Chaiken (1993). "A Dynamic Model of the Duration of the Customer's Relationship with a Continuous Service Provider: reacquired at higher prices have longer second tenures. "The Alloca- egy. Kannan. 24 (2). Thomas (2001). Ajay Kalra. firms must prior history be concerned and/or current response. "Similarities in Choi reacquired. Con- The Role of Satisfaction. however. our analysis shows Blattberg. there are some limitations and ion Quarterly. 105-112. Andrew and Peter E. tive prices. ble. related to individual-level remarketing efforts. A betterdemandstrategy becomes a functionforof marketing maximiz. This Gibbs Sampler. quisition is the critical phase in the winback initiative. that have relatively standard costs across customers in their Eagly. and Jacquelyn S.K." Journal of Industrial Econom- spending levels should vary on the basis of the customer's ics." The American Statistician. the firm should focus on maximizing (1)." the relationship has been reestablished. Regression Model. 17 (1). our research suggests that lapsed customers who are more likely to be reacquired have REFERENCES a shorter second tenure with the firm after they have been Ainslie. duration of the second tenure. 29 metric of interest. Many firms make reacquisition offers conditional on customers' Early CRM advocates touted the benefits of having responses to prior offers. our findings apply to firms (4). particularly for reacquisition pricing. Michael A. George (1992). If market share is the OMEGA: The International Journal of Management Science. A paucity of cost data prevents us Marketing Decision Making. winback Generalized Consumer Choice. individual. 95-108." Journal of Econometrics. cus." Marketing Science. 51 (1-2). "Explaining the ative to the prior price result in longer second tenures. "Manage Market- that both reacquisition and retention prices should be low. 79-99. 171-86. FL: Harcourt Brace Jovanovich. price increases have Boulding. 297-318." Harvard Business Review.6. 91-106. firms should increase prices when tion of Promotion Budget to Maximize Customer Equity. In particular. Series B (34). . 44 JOURNAL OF MARKETING RESEARCH. our research shows that there is a . Arthur R. However. no affect on second tenure duration.jstor. "Attitudinal Consequences of Induced dynamic pricing and the customer's prior history with the Discrepancies Between Cognitions and Behavior. 187-200. "Regression Models and Life Tables." Public Opin- firm to a winback strategy. Siddhartha (1993). ing by the Customer Equity Test. Boston: Harvard Business School Press. is an example of this. reenter the relationship. To maximize profits. customers respond and Katherine N. it would be useful to address price endogeneity (Villas-Boas and DISCUSSION AND LIMITATIONS Winer 1999). 42 (March). Our analysis shows that reac. Rossi (1998). after the relationship is reestablished. It is not worth it for firms to try to reestab- the dynamics of customer winback and foster insights into lish relationships with customers who are likely to lapse or dynamic pricing strategies. this research shows that lapsed consumers' (July-August).

"Pricing Decisions Under Demand . Hogarth (1981). 85 (410)." Marketing Science. (2001). 59 (2). Marketing. Handbooks in This content downloaded from 193. 199-214. Customer Win. ing Corporate Strategy." Journal of Consumer Research. Bass (1993). (Winter). keting. 38 (May). 398-409. Reinartz. tomer Relationships as Markov Chains. Rev." Catalog Age.53-88." Marketing Science. Katherine N. Richard (1985). "Regaining Service Generalizations from Reference Price Research. "Back to Life. (1957). Thaler.. AMarple. 16 (2). Research. ers and Stayers. 1 (4). Lowenstein (2001). tomer Acquisition to Customer Retention. Morrison. "Understanding the Customer Base of Service Reichheld. 7-59." Marketing Science. Dipak and Siddhartha S. "Mental Accounting and Consumer Keaveney. 387-400.(1964). 68 Approaches to Calculating Marginal Densities. 65-87. Conflict. Werner and V. New York: The Free Press. Samuelson. "Counting Your Customers: Who Are They An Analysis of Decision Under Risk. Mark and Michael Theory Zimmerman of (1999). Chicago: Irwin Professional Publishing. and S. "The Role of Price Per- Krishnamurthi. 153-61. 45-49. Customers. Decision. American Statistical Association." Journal of Market." Cat- Value Research in Marketing: A Review and Future Directions. Choice. 64 (October). 232-40. Bias in Decision Making.6. Kristiaan and David Schmittlein (1993). Sajeev and Mark Colgate (2001). and Richard Kahneman. Hansotia. Zeithaml. "The 8 Commandments . Depart Heckman.Villas-Boas. San Francisco: Jossey-Bass." Marketing Industrial Purchase Process Application. "Modeling Cus- Stanford University Press.L.and Robert Peterson (1994). and Paul Wang (1997). Boston: Har- Providers: An Examination of the Differences Between Switch. vard Business School Press.P. Earl Sasser Jr. Schmittlein. Operations Research "Behaviora and Management Science. 34-46. ." Journal of Direct Marketing. 13 Science. ence. Varki. Singh (2002). ceptions in an Integrated Model of Behavioral Intentions. 47 and What Will They Do Next?" Management Science. "New 1324-38." Econometrica. "Customer Lifetime Schmid. Lilien." Journal of Service Research.. of Design. "Status Quo Hughes. Winer (1999). Vol. Tridib Mazumdar. Eitan Muller. 349-408." Marketing Sci." Harvard Business Review. Lemon (2000). 15 (1). 71-82. (1995). The Loyalty Effect.." Journal of Marketing. and K (2000)." Journal of Risk and Uncertainty. Jacquelyn S." in Marketing. 23 Nov 2017 16:02:55 UTC All use subject to http://about. Winer (1995). Raj (1992). Jill and Michael W. 14 (3). "Zero Defections: Quality Gelfand. Miguel and Russell S. 347-61. and Frank M. 262-68. 7-19. (March). 43-55. Smith (1990). 41-67. 33 (1). (1). Roland T. Mahajan. 1-24. (2001). J. James (1979). "Empirical Stauss. ard Rate Models. Valarie A. (1990). University of Maryland. ving Customer Equity: How Customer Lifetime Value Is Reshap- tion Times in Marketing: Evidence for the Effectiveness of Haz. "Driving Customer Equity: Linking Customer Lifetim 11 (2). 45 (October). 57-64. Recapturing Lost Customers 45 . and Robert Dissonanc L. Frederick F. "Sampling-Based Comes to Services." working paper. Kirthi (1996)." Journal of Mar- Loyal. 4 (Summer). Dri- Helsen. Purchase Quantity Decisions. and Katherine N." Journal of the (September-October). Susan M. Product Diffusion Models. Phillip E." Mortgage Banking.jstor. Lemon.M." Econometrica. Festinger. (1996). "Customer Switching Behavior in Choice. 3 (3). Jain. 11 (4). 37-38. Carraway (2000). and Robin M. 64 (July).. David C. 13 (2). Kalyanaram. Journal of Interactive Marketing.21 on Thu. Mark 14 (2). 47 (January). Donald G. Kalyanam. 5. 207-221. Lakshman. and W. "On the Profitability o Griffin. in Brand Choice Models. G161-G169. 105-111. L. Jaishankar. Retention Strategy. Long-Life Customers in a Noncontractual Setting: An Empirical back: How to Recapture Lost Customers-And Keep Them Investigation and Implications for Marketing. Peterson. (1996). Arthur M. Value to Strategic Marketing Decisions. and Pfeifer. "A Customer Di Cognitive IL: Row. "Prospect Theory: Colombo (1987)." Jour- "Asymmetric Response to Price in Consumer Brand Choice and nal of Service Research. Service Industries: An Exploratory Study. "Analyzing Dura." eds. and Valarie A. 15 (3). 263-91. J.175. William and Richard Zeckhauser (1988). Gurumurthy and Russell S. Amsterdam: North-Holland." Journal of Interactive Ganesh." Management Science. Vijay. Bernd and Christian Friege (1999). 17-35. . 395-414. Arnold. "Endogeneity 19 (3)." alog Age. 59 (11). "Customer Base Analysis: An Uncertainty: A Bayesian Mixture Model Approach. Kumar (2000). Thomas. and Adrian F. "A Methodology for Linking Cus- ing. 32. Alan E. "Sample Selection Bias as a Specification ment of Marketing. Daniel and Amos Tversky (1979). Kathleen (1996). Behram J. "Analytical Chal. Error. 1 ed. Zeithaml lenges in Customer Acquisition. Jehoshua ory: Process of Eliashberg and and Judgment G.org/terms ." Journal of Marketing Kiley. Annu chology.Rust. Jack (1998). The Complete Database Marketer.