Professional Documents
Culture Documents
Marketing Science
Publication details, including instructions for authors and subscription information:
http://pubsonline.informs.org
. http://dx.doi.org/10.1287/mksc.2015.0953
This article may be used only for the purposes of research, teaching, and/or private study. Commercial use
or systematic downloading (by robots or other automatic processes) is prohibited without explicit Publisher
approval, unless otherwise noted. For more information, contact permissions@informs.org.
The Publisher does not warrant or guarantee the article’s accuracy, completeness, merchantability, fitness
for a particular purpose, or non-infringement. Descriptions of, or references to, products or publications, or
inclusion of an advertisement in this article, neither constitutes nor implies a guarantee, endorsement, or
support of claims made of that product, publication, or service.
INFORMS is the largest professional society in the world for professionals in the fields of operations research, management
science, and analytics.
For more information on INFORMS, its publications, membership, or meetings visit http://www.informs.org
Articles in Advance, pp. 1–14
ISSN 0732-2399 (print) ISSN 1526-548X (online) http://dx.doi.org/10.1287/mksc.2015.0953
© 2015 INFORMS
Olivier Rubel
University of California Davis, Davis, California 95616, orubel@ucdavis.edu
Ashutosh Prasad
University of Texas at Dallas, Richardson, Texas 75080, aprasad@utdallas.edu
T o inform the design of sales force compensation plans when carryover effects exist, we propose a dynamic
model where these effects, together with present selling efforts, drive sales. Our results show that a salesperson
with low risk aversion exerts effort to decrease attrition from existing business, whereas a salesperson with high
risk aversion does not. Why? Because carryover increases not only expected sales but also sales uncertainty.
Consequently, the manager should incentivize the high risk-aversion salesperson with a concave compensation
plan to counterbalance suboptimal customer attrition, and the low risk-aversion salesperson with a convex
compensation plan that limits coasting on past efforts. We generalize our results to when the firm employs
multiple salespeople, and when advertising and personal selling are budgeted together.
Keywords: sales force; compensation; sales dynamics; agency theory; differential games; advertising
History: Received: February 10, 2014; accepted: July 1, 2015; Fred Feinberg served as the senior editor and John
Zhang served as associate editor for this article. Published online in Articles in Advance.
between two goals; generating new business and man- extends this static approach where compensation is
aging attrition from existing business. A salesperson based on total sales and not on sales dynamics, to a
with a low risk aversion works toward decreasing dynamic setting.
customer’s attrition, whereas a salesperson with a high The sales force compensation literature offers little
risk aversion does not. Why? Because the carryover managerial guidance about how to incentivize strategic
effect increases both the mean and the variance of future sales agents when carryover effects exist. On one
sales. This insight implies that a high risk-aversion hand, early literature informing allocation decisions of
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
salesperson gets more disutility from the additional personal selling efforts over time omit agents’ strategic
uncertainty generated by carryover effects. As a result, behaviors (e.g., Beswick 1977, Darmon 1978, Tapiero
whereas a salesperson with low risk aversion wants to and Farley 1975). On the other hand, although several
increase sales by strategically influencing attrition, a mechanisms have been discovered to mitigate the risk
salesperson with high risk aversion does not, to reduce of moral hazard, limited predictions exist to anticipate
future uncertainty. Thus, selling efforts make uncer- the outcomes of the dynamic agency relationship when
tainty endogenous when carryover effects exist. We sales are dynamic (e.g., Albers and Mantrala 2008,
find that when the salesperson has a high level of risk Coughlan and Joseph 2012). In particular, the dynamic
aversion compared to the noisiness of the sales response sales force literature offers only partial predictive
function, the manager should implement a concave insights on how the interaction between sales carryover
compensation plan to countervail suboptimal customer effects and risk aversion shapes the outcomes of the
attrition and incentivize new sales. Conversely, when agency relationship (e.g., Caldieraro and Coughlan
the salesperson has a low risk aversion compared to 2009, Lal and Srinivasan 1993, Krishnamoorthy et al.
the noisiness of the sales response function, the firm 2005, Mantrala et al. 1997). Framing precise guidelines
should implement a convex compensation plan with requires understanding the full role of sales dynamics
a threshold to disincentivize coasting on past effort. on the effort decisions by the salesperson and the effect
Finally, we examine how our results change when of compensation in moderating effort.
the manager employs multiple salespeople and when Dynamics in principal-agent models have been stud-
the firm shares the communications budget between ied in multiperiod models (e.g., Laffont and Martimort
selling and advertising. 2002, §8) where a good description of the repeated
contracting between firms and salespeople is infinitely
repeated moral hazard relationships introduced by
2. Literature and Contributions Spear and Srivastava (1987). A simplified, two-period
The principal-agent framework is widely used to under-
setting is considered by Laffont and Martimort (2002,
stand the contracting relationship between the sales
§8.2.6). These papers omit within-period dynamics and
manager representing the firm, and the salesperson.
show that constant high effort level is induced in each
These models have the following structure. Let x denote
period. Holmstrom and Milgrom (1987) examine sales
observable sales and v denote unobserved effort, and
dynamics and show that a linear contract is optimal
let their relationship follow the distribution f 4x1 v5 with
when sales follow a Brownian motion where the drift
support on 6 x1 x̄7. Then the firm’s goal is to provide a
term depends solely on the salesperson’s effort and
compensation S4x5 such that
not on current and past effort as in our case. Sannikov
Z x̄ (2008) and Williams (2011, 2013) provide dynamic
max 4x − S4x55f 4x1 v5 dx1 agency models where agent’s observed performance
S4x5 x
relies also on current effort, similar to Holmstrom
subject to the salesperson’s individual rationality (IR) and Milgrom (1987), and solve the dynamic problem
and incentive compatibility (IC) constraints, which are, through a martingale approach.
respectively, Our model shares some common features with these
dynamic agency models in that we consider a Brownian
Z x̄
U 4S4x55f 4x1 v5 dx − C4v5 ≥ R1 process where the sales agent’s effort is a part of the
x drift term and that the salesperson has a utility function
x̄ that exhibits constant risk aversion. However, we differ
Z
v = arg max U 4S4x55f 4x1 u5 dx − C4v5 1 from them in important ways, viz., the introduction
u x
of sales carryover makes the problem fully dynamic,
where U 4 · 5 is the utility from compensation, C4 · 5 is the and the solution is parsimonious since it does not
disutility from effort, and R is the outside reservation require the construction of the agent’s continuation
utility for the sales agent (see, e.g., Holmstrom 1979, value with the martingale representation theorem (see,
Basu et al. 1985). For different specifications of the e.g., Sannikov 2008). Consequently, we show that the
utility function and sales response function, differ- optimal compensation plan can be either convex or
ent compensation plans will be obtained. Our model concave, and contrary to the recent dynamic agency
Rubel and Prasad: Dynamic Incentives in Sales Force Compensation
Marketing Science, Articles in Advance, pp. 1–14, © 2015 INFORMS 3
literature (e.g., Sannikov 2008; Williams 2011, 2013), the Table 1 Notation
dynamic optimal contract does not need to be based
Symbol Description
on the agent’s latent continuation value as it suffices to
offer a compensation plan that is a quadratic function t ∈ 601 5 Timeline continuum.
of observed sales. Finally, our results add to the dynamic x4t51 dx4t5/dt Sales and sales rate at time t, respectively.
1 Sales attrition parameter and sales carryover
agency literature in that we allow the principal to have parameter, respectively. Note that + = 10
an impact on the performance measure through its
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
1 2
Moreover, the firm, at least in theory, is infinitely lived, and The Brownian motion captures market uncertainties over the
salespeople spend time developing relationships with clients and probability space (, ì, F), where ì is the countable set of all
the firm keeping the long term in mind. Finally, a finite horizon possible sales realizations, F is the filtration generated by B, and is
analysis would suppose a terminal stock target, but to compute a probability measure such that for any time period t, 2 Ft → 601 17,
the appropriate terminal stock requires taking the future after the with 45 = 0 and 4ì5 = 1. In managerial terms, Ft encodes the
horizon into account. available information up to time t.
Rubel and Prasad: Dynamic Incentives in Sales Force Compensation
4 Marketing Science, Articles in Advance, pp. 1–14, © 2015 INFORMS
of functions. We focus on the latter. The nonlinear contribution of an incremental sale to the value function.
optimal solution can later be approximated in terms of Finally, the term 4Vxx − Vx2 5/2 captures the impacts of
commonly used compensation components, such as uncertainty (since Var6dx/dt7 = 5 on the value function,
straight salary, commission, and quota (e.g., Basu and where −Vx is the additional cost of uncertainty borne
Kalyanaram 1990). because of risk aversion.
Differentiating (3) with respect to v and equating the
3.3. Salesperson Utility resulting expression to zero, we obtain the first-order
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
The salesperson incurs the cost C4v4t55 from the selling condition
effort v4t5. A convex cost function, i.e., C 0 > 0 and v∗ = Vx 1 (IC)
C 00 > 0, is assumed and we use the common specifica-
tion C4v4t55 = v4t52 /2. The salesperson is compensated which defines the salesperson’s IC condition. Inserting
with the plan S4x4t55 that varies with observed sales x4t5. it back into the HJB, we obtain the agent’s IR condition
We note that the solution concept of Markov perfect V 4x5 ≥ R0 (IR)
(closed-loop) equilibrium is standard in the marketing
and management science literature.3 Consistent with 3.4. Firm’s Objective
the literature, the state variable is sales, x4t5, which The manager designs the optimal compensation plan
encapsulates the profit relevant information for the firm. to maximize the firm’s long-term profit while ensur-
Hence, effort and compensation decisions are functions ing that the salesperson’s IR and IC constraints are
of sales, and the optimal decisions are truly optimal respected. The firm’s long-term profit is
and not just in a class of prespecified functional forms. Z
The time argument t will henceforth be suppressed Ɛ −rt
e 8x − S4x59 dt
when no confusion arises. 0
The salesperson is assumed to be risk averse with
and its value function is given by
a concave utility function that exhibits constant risk
aversion (e.g., Holmstrom and Milgrom 1987), such Z
−rt
that the long-term utility of the salesperson is given by ç4x5 = max Ɛ e 8x − S4x59 dt 1
S4x5 0
Z
J 4x5 = E − exp − e−rt 8S4x5 − v2 /29 dt 0 (2) subject to (1), (IC), and (IR). As a result, the firm’s HJB
0 equation is
Here, r is the discount rate, E is the expectation operator,
rç4x5 = max x − S4x5 + çx 4Vx − x5 + çxx /2 1 (4)
and > 0 is the risk-aversion parameter. S4x5
4 − 15 41 − 5
Uncertainty of existing business
24A2 + 5 24B2 − 5
Where the value function of the firm satisfies the salesperson’s behavior. Specifically, a salesperson
( with a high risk aversion suffers more from the addi-
A1 + A2 x1 < 1/1 tional uncertainty generated by the carryover effect
çx =
B1 + B2 x1 > 1/0 and thus favors decreasing uncertainty by reducing
carryover sales by the factor 1 + 1/4 − 15. Conversely,
Expressions for constants A1 > 01 A2 < 0, B1 > 01 and a salesperson with low risk-aversion favors increasing
B2 < 0 are in the appendix. future sales by curbing attrition and thus decreases
Proposition 1 shows that the salesperson’s effort is by the factor 1 − 1/41 − 5 < 1.
allocated between two goals—generating new business Allocation of Selling Efforts. The impact of this asym-
and managing attrition from existing business. To metric behavior also manifests in how the salesperson
make this interpretation, replace the optimal effort allocates selling efforts between old and new business.
expressions from Proposition 1 into the sales dynamics Why? Because under the optimal effort strategy of
given in Equation (1), to obtain the salesperson, the levels of uncertainty for new and
old business converge to different stationary mean
1 1 values; see Table 2. Specifically, the level of uncertainty
4A + A x5 − 1 − x
1 − {z1 2 surrounding new business can be lower, higher, or
1 −
equal to the level of uncertainty surrounding existing
| } | {z }
New business Equilibrium
√ attrition rate business.
+ t 1 < 1/1
dx
Moreover, how much new business is generated is
= (5) proportional to how much the firm values a marginal
dt 1
1
− 1 4B1 + B2 x5 − 1 + − 1 x
sale, i.e., çx (see (19) in the appendix), which enters
| {z } | {z } the firm’s optimal compensation strategy. This shadow
New business Equilibrium price decreases as x increases, due to concavity of the
attrition rate
√
firm’s value function with respect to sales, i.e., çxx < 0.
+ t 1 > 1/0
Hence, the manager has fewer incentives to motivate
Labeling the two cases < 1/ and > 1/ as low the salesperson to work hard for a new sale. Moreover,
risk aversion and high risk aversion, respectively, we as sales increase, so does the number of customers who
observe that the salesperson manages sales attrition can potentially leave the company, which increases the
differently depending on their level of risk aversion. effort and hence the cost that the agent would have to
A low risk-aversion agent works to reduce the rate put to retain existing business.4 Therefore, how the
of sales attrition, or said differently to increase car- agent allocates efforts between generating new and
ryover, since 1 − 1/41 − 5 < 1. Conversely, a high existing business is driven by sales uncertainty and
risk-aversion salesperson works to increase attrition or how the manager compensates the salesperson through
decrease carryover, because 1 + 1/4 − 15 > 1, which the incentive plan, which we detail next.
can manifest in the field, for instance, by the salesper-
son not following up with existing clients and focusing 5. Optimal Compensation Plan
mostly on generating new sales.
To understand why these different behaviors emerge Proposition 2. For a low risk-aversion salesperson
especially when the salesperson has a high risk aversion, 4 < 1/5 the optimal compensation plan is convex in sales.
we first compute the mean and the variance of sta-
tionary distribution of x4t5∗ , i.e., Ɛ6x4t5∗ 7 and Var6x4t5∗ 7, 4
Thus, if the company has 100 customers and the carryover is 75%
respectively (the formula is reported in Corollary 1 (as reported in Albers et al. 2010), the agent would have to focus on
25 existing customers who might churn, while when the company
in the appendix). Next, by differentiating E6x4t5∗ 7 and
has 1,000 customers, the agent would have to focus on 250 customers
Var6x4t5∗ 7 with respect to the carryover effect, reveals who might churn. Hence the costs of managing new and existing
that it increases not only expected future sales but also business vary as sales vary, which ultimately impact how the agent
expected variance, which provides some insights about works new and existing business.
Rubel and Prasad: Dynamic Incentives in Sales Force Compensation
6 Marketing Science, Articles in Advance, pp. 1–14, © 2015 INFORMS
1 2 > 1
Compensation S(x)
Compensation S(x)
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
1
2 > 1
Sales x Sales x
For a high risk-aversion salesperson 4 > 1/5 it is concave the agent’s level of risk aversion. Based on numeri-
in sales. Specifically, cal simulations,5 we find that in the case of the low
( risk-aversion agent, an increase in the carryover effect
∗ max803 a0 + a1 x + a2 x2 91 < 1/1 increases the threshold and decreases the “convexity”
S4x5 = of the plan. Such a result is intuitive as the manager
b0 + b1 x + b2 x2 1 > 1/0
internalizes that fact that more sales come from accu-
Where the constants are mulated efforts with the account. Thus, it is optimal
to increase the threshold after which the salesperson
4 + A2 5 + A21 A1 A2 starts being compensated.
a0 = − < 01 a1 = − > 01 and
241 − 5 1 − In the case of the high risk-aversion agent, the salary
4A2 − 54A2 + 5 4 − B2 5 + B12 offered to the agent is larger than the value of the
a2 = − > 03 b0 = > 01 outside option, and it increases as the carryover effect
241 − 5 24 − 15
increases. The total compensation also increases as the
B1 B2 4B2 − 54B2 + 5 carryover effect increases. These two insights comport
b1 = > 01 and b2 = < 00
− 1 24 − 15 with our earlier finding that as the carryover effect
increases, so does the level of risk to which the agent is
In both cases the optimal compensation plan is exposed, which then requires a higher salary to ensure
quadratic in sales, which is a tractable form for theory that the agent works for the firm.
and implementation. Specifically, for low risk-aversion To put these results in perspective, we note that
salespeople, the optimal compensation plan is convex several studies document that sales force compensation
as a2 > 0. Note also that there is a discontinuity due to plans are often shown or assumed to be convex in
the corner solution, and it specifies that when sales sales to overcome the increasing marginal cost of effort
are below a threshold level such that the expression of the agent to incentivize effort even at high levels
a0 + a1 x + a2 x2 is negative, the salesperson is paid a of sales. In dynamic settings, however, Holmstrom
salary equal to the outside option (scaled to zero). and Milgrom (1987) show that the optimal contract
Above this threshold, the compensation is convex in is linear. Meanwhile, additional research shows that
sales. Thus, when the agent has a low level of risk instead of a convex or linear compensation plan, man-
aversion, the firm implements a convex compensation agers often implement concave compensation contracts
plan that disincentivizes coasting on past efforts with a (e.g., Mantrala and Raman 1990, Hauser et al. 1996,
threshold, e.g., by implementing a quota. Mantrala et al. 1997, Barnes 1986, Churchill et al. 1996).
Conversely, the optimal compensation plan for the Proposition 2 adds to these insights by revealing that
high risk-aversion agent is concave in sales. Why? the optimal compensation is either convex or concave,
Because the carryover effect increases sales variance. depending on the sales agent’s risk aversion, relative
Hence, the plan incentivizes the high risk-aversion sales to the noisiness of the sales response function.
agent to bring sales on target, despite the increased The results in Proposition 2 add to Mantrala and
uncertainty resulting from the carryover effect. This Raman (1990), Hauser et al. (1996), and Mantrala et al.
result aligns with the insight of Zoltners et al. (2006) (1997) not only in showing that a concave compensation
that concave compensation plans provide “protection”
against demand uncertainty. 5
Simulations were conducted with the function “Manipulate” imple-
Figure 1 illustrates how the carryover parameter mented in Mathematica 10 with the parameter values 1 − = ∈
alters the optimal compensation plans depending on 601 0057, r ∈ 601 17, and ∈ 601 37.
Rubel and Prasad: Dynamic Incentives in Sales Force Compensation
Marketing Science, Articles in Advance, pp. 1–14, © 2015 INFORMS 7
plan can indeed be optimal but also in providing a we derive Ɛ6dS ∗ /dt7 by applying Ito’s lemma and
rationale as for why managers should implement such find that
¡S ∗ dx ¡ 2 S ∗
∗
plans, i.e., to countervail suboptimal customer attrition dS
Ɛ = + 1
by the high risk-aversion salesperson. dt ¡x dt ¡x2 2
Our results also add to the findings in Basu et al.
which reveals how the compensation plan evolves
(1985), where risk aversion also determines conditions
over time with respect to changes in sales. We then
for convex and concave shaped compensation plans.
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
∗
vi =
çNx x 2N − 1 6.2. Advertising and Sales Force
− 1 > 0
We begin by noting that despite the fact that firms
+ } |1 − 2N + }
1 − 2N
usually use both advertising and personal selling to
| {z {z
Effort on
Effort on
new business existing business sell brands, few insights exist about how to optimally
use advertising with sales force contract design. An
Where the value function of the firm satisfies exception is Murthy and Mantrala (2005) who provide
( guidelines on how managers should allocate market-
¡çN AN 1 + AN 2 x1 < 42N − 15/1 ing resources to advertising and sales contests taking
= çNx =
¡x BN 1 + BN 2 x1 > 42N − 15/0 into account the agency relationship and the related
contractual problem.
Expressions for constants AN 1 > 01 AN 2 < 01 BN 1 > 0, and Building on our earlier results, we augment the
BN 2 < 0 are in the appendix. sales dynamics (1) to generalize it to situations where
(b) The optimal compensation plan is convex (or concave) sales are not only driven by the agent’s selling efforts
in sales when < 42N − 15/ (or > 42N − 15/50 but also by advertising, such that the sales dynamics
Proposition 3 is qualitatively similar to Propositions 1 becomes
and 2 in that, first, sales agents’ efforts are directed √
toward the two goals of generating new business and dx/dt = v4t5 + u4t5 − x + t 1 x405 = x0 1 (10)
managing attrition of existing business, and, second, where u4t5 is the firm’s advertising effort and its
that the optimal compensation plan can be convex or effectiveness on sales such that if > 1 advertising is
concave depending on . more effective than personal selling, and vice versa if
Proposition 3, however, reveals two new insights. < 1. By setting = 0 we recover the main model. In
First, it shows that the threshold level above (or below) such situations, the salesperson’s HJB equation is now
which the firm should offer a concave (or convex)
compensation plan to agents increases in the number rV 4x5 = max S4x5 − v2 /2 + Vx 4v + u − x5
v
of agents, N . Thus, a prediction is that firms managing
a larger sales force are more likely to provide convex + 4Vxx − Vx2 5/2 1 (11)
compensation plans than firms employing a smaller
which yields the IC condition v∗ = Vx and the IR
sales force.
condition 41/r54S4x5 + Vx2 41 − 5/2 + Vx 4u − x5 +
Second, using the results from Proposition 3 allows
Vxx /25 ≥ R.
us to investigate how the optimal strategies vary with
The manager determines both the optimal contract
the number of agents. Owing to the intricate mathe-
and advertising strategy so as to maximize the firm’s
matical expressions for the equilibrium strategies, we
long-term profit. Let u2 /2 represent the cost of adver-
conduct such investigations numerically,6 and obtain
tising. Then the manager’s problem is
the following insights, (i) when < 42N − 15/ agents
exert less effort as N increases, as a result, the manager Z
increases quotas and decreases total compensations. ç̃4x5 = max Ɛ e−rt 8x − S4x5 − u2 /29 dt 1
8S4x51u9 0
Conversely, (ii) when > 42N − 15/, agents exert more
effort as N increases since the manager increases total subject to Equation (11) and the new IC and IR
compensations. The numerical findings comport with conditions.
our previous results in that when agents have a low We solve for the optimal strategies and value func-
risk aversion, the manager’s optimal strategy is to tions in the appendix and find that the optimal com-
implement a convex compensation structure with a pensation plan comports with our earlier results in that
threshold to prevent agents from coasting on free sales for low risk-aversion salespeople the optimal compen-
(Zoltners et al. 2006) that are generated by past efforts. sation plan is convex in sales. For high risk-aversion
Interestingly, when agents have a high risk aversion, salespeople it is concave in sales. Three additional
insights are obtained from the analysis of the optimal
6
Simulations were conducted with the function “Manipulate” im- strategies.
plemented in Mathematica 10 with the parameter values 1 − = ∈ First, we learn that similar to the salesperson, the firm
601 00571 r ∈ 601 171 ∈ 601 47, and n = 811 21 0 0 0 1 109. advertises to achieve two goals, namely, increase new
Rubel and Prasad: Dynamic Incentives in Sales Force Compensation
Marketing Science, Articles in Advance, pp. 1–14, © 2015 INFORMS 9
business and manage attrition. Specifically, when < 1/, the optimal promotion budget and total promotional
the manager allocates max801 −/41 + 2 − 5ç̃x1 1 9 impact decrease as sales increase when the agent has
to generate new sales and x/41 + 2 − 5 to con- a low level of risk aversion, i.e., ¡B4x5/¡x < 0 and
trol attrition; and when > 1/, the manager al- ¡M4x5/¡x < 01 thus obtaining an inverse allocation
locates max801 −/41 + 2 − 5ç̃x1 2 9 and x/ rule, which has been prescribed in some papers on
41 + 2 − 5, to new and existing business, respectively. advertising dynamics, e.g., Prasad and Sethi (2005).
Second, despite the existence of no direct interaction However, this and the preceding result have not been
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
between the promotional tools, variations in impact reconciled previously as both being optimal strategies,
how the salesperson works. Without the agency rela- especially when one of the instruments is personal
tionship, and if the manager could directly control both selling. We now conclude and explain how our results
u and v, this would not happen because the dynamics inform the sales force compensation practice.
will resemble Naik and Raman (2003) without the inter-
action term. Third, we find that for ∈ 61/3 41 + 2 5/7,
i.e., when a salesperson’s level of risk aversion is inter- 7. Conclusions
mediate, the optimal strategies equal zero, which means Improvements in understanding compensation design
that the firm cannot optimally use both advertising and in dynamic markets are worthwhile since companies
personal selling to sell the product and must therefore invest about $800 billion in personal selling, or about
use only one instrument. three times what they spend on advertising (Albers
Furthermore, using these new insights, and the and Mantrala 2008). Similar to advertising, personal
mathematical expressions for the optimal contracts selling activities can have a long-term effect on sales
(reported in the appendix), we obtain new results on (Albers et al. 2010). Yet, contrary to the well-developed
the management of promotion budgets by firms when dynamic policies of advertising, very few studies pro-
an agency relationship exists. vide normative guidelines to help managers maximize
Specifically, when the manager uses both advertising the returns-on-investment of incentive compensation
and personal selling to sell the firm’s brand, the total plans in dynamic markets. We provide an analytical
promotional budget, i.e., B4x5, equals the sum of the treatment of the optimal design of sales force compen-
sales force compensation and advertising expenditures, sation contracts when sales carryover effects exist, that
such that B4x5 = S4x5∗ + u∗2 /2. Consequently, the share is when sales is understood as a dynamic variable.
of sales force compensation in this budget equals By addressing this lacuna in the compensation design
å1 4x5 = S4x5/B4x5. Meanwhile, the actual total effort literature, we identify important factors that shape
that is generated by both the firm and the agent is the outcomes of a sales force agency relationship in a
M4x5 = v∗ + u∗ . Hence, the share of personal selling dynamic market. The model shares assumptions with
in the total promotional effort is different than the dynamic agency literature but has significant differ-
share of the sales force compensation in the firm’s ences, i.e., carryover sales, infinite horizon, closed-loop
budget, i.e., å2 4x5 = v∗ 4x5/M4x5. Said differently, owing concept, inclusion of advertising, and time discounting.
to the nature of the promotional instruments, we find Several analytical propositions are developed and the
that å1 4x5 6= å2 4x5, which means that the impact ratio results are based on explicit analytical results rather
of the promotional instruments is different from the than numerical simulations. Most important, the pro-
budget allocation. Using these results on the optimal posed approach yields answers to the managerial
promotion budgets and allocation rules, we obtain the questions raised by dynamic sales.
following proposition. We first discover that the degree of risk aversion of
the salesperson, relative to the noisiness of the sales
Proposition 4. When the agent has a low level of risk response function, plays an important role in determin-
aversion, the manager adopts a proportional to sales budget-
ing the effort strategy of the salesperson and the optimal
ing strategy, i.e., ¡B4x5/¡x > 0.
contract in the presence of carryover effects. This insight
However, when the agent has a high level of risk aversion,
manifests because the carryover effect increases both
the manager adopts an inverse to sales budgeting strategy,
the mean and the variance of future sales.
i.e., ¡B4x5/¡x < 0.
As a result, we find that the shape of the optimal
Finally, in both cases, the share of personal selling in the
compensation plan is convex in sales for a low risk-
total promotional budget increases as sales increases, i.e.,
aversion salesperson and concave in sales for a
¡å1 4x5/¡x > 0, whereas its share in the total promotional
high risk-aversion salesperson, which answers our first
impact decreases, i.e., ¡å2 4x5/¡x < 0.
research question. This finding is significant because
The first part of Proposition 4 comports with the whereas there is evidence of the use of concave compen-
managerial heuristics of budgeting marketing re- sation plans (e.g., Mantrala et al. 1997), the literature
sources proportional to sales, as documented in the has examined mainly convex and occasionally linear
advertising literature (Farris et al. 1998). Conversely, plans as optimal. We show that both forms are obtained
Rubel and Prasad: Dynamic Incentives in Sales Force Compensation
10 Marketing Science, Articles in Advance, pp. 1–14, © 2015 INFORMS
1. The carryover effect increases both the mean and the variance of sales. Prior findings have not considered the role of carryover in the volatility
of sales.
2. Low risk-aversion salespeople will prefer increased carryover and reduced No study investigates the dynamic allocation of selling efforts by a salesperson
sales attrition. High risk-aversion salespeople will prefer the opposite and when sales carryover effects exist.
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
from the same model thereby providing a resolution for the estimated parameters to design the appropriate
the discrepancy between theory and practice. compensation plan based on the results provided by
Proposition 1 then reveals that the optimal effort Proposition 2. Finally, a chief marketing officer can
strategy of the salesperson is driven by allocation con- use our results in §6 to strategically allocate resources
siderations. According to this result, a low risk-aversion between advertising and sales taking into account the
salesperson, who cares more about mean sales and agency relationship.
(relatively) less about variance, will work to increase
carryover and reduce sales attrition. On the contrary, a Acknowledgments
high risk-aversion salesperson will care more about The authors thank the senior editor, associate editor, and two
variance and focus on new sales generation. Thus, anonymous reviewers for their insightful comments.
Proposition 1 answers our second research question. Appendix
Proposition 1 also shows the quadratic form of the
firm’s value function including the dependence on the Proof of Proposition 1. The dynamic optimal control
problem faced by the salesperson is to determine the effort
carryover effect.
strategy, v4t5, that maximizes long-term utility
Moreover, we consider the inclusion of advertising Z
budgeting considerations on the design of the compen- J 4x5 = Ɛ −exp − e−rt 8S4x5−C4v4t559dt 1 (12)
sation plan. Results show that whereas the coefficients 0
selling in the total promotional effort of the firm. Thus, + 4Vxx − Vx2 5/2 1 (14)
Proposition 4 addresses our third research question. where = 1 − (see, e.g., Bensoussan and Elliott 1995). After
Table 3 provides a summary of the main results and replacing C4v5 by v2 /2, we differentiate (14) with respect to v
comparisons with the literature. and equate the resulting expression to zero to obtain the
We close by explaining how our findings inform necessary condition
practice. The proposed model relies on a dynamic sales v∗ = Vx 0 (15)
response model that is extensively used in empirical Equation (15) is the salesperson’s IC condition. Next we
research in marketing. To implement our findings, replace (15) in (14) to find that the value function equals
managers should first jointly estimate the sales dynam- 1
S4x5 + Vx2 41 − 5/2 − Vx x + Vxx /2 0
ics and the unobserved effort strategies provided in V 4x5 = (16)
r
Proposition 1, via a Kalman filter, for example. On
From (16), the IR condition of the salesperson is
recovering the response parameters, a sales manager
S4x5 + Vx2 41 − 5/2 − Vx x + Vxx /2 r ≥ R1
or consultancy like ZS Associates, could then use (17)
Rubel and Prasad: Dynamic Incentives in Sales Force Compensation
Marketing Science, Articles in Advance, pp. 1–14, © 2015 INFORMS 11
where R is the value of the outside option. Corollary 1. Equilibrium sales, x4t5∗ , are normally dis-
The risk-neutral firm determines the compensation
R plan, tributed, with mean and variance as follows. For a low risk-aversion
S4x5, to maximize the long-term profit Ɛ6 0 e−rt 8x − S4x59 dt7, salesperson
subject to sales dynamics, the IC, and the IR conditions, i.e.,
(12), (15), and (17), respectively. A1
Ɛ6x4t5∗ 7 = − > 01 and
Normalizing R to zero without loss of generality and A2 +
assuming that (17) binds, we solve (17) as a quadratic in Vx 4 − 15
Var6x4t5∗ 7 =
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
value function in equilibrium equals −2 /442r41 − 555x2 + Differentiating (21) with respect to S4x5 yields the necessary
x/r + 4r − 5/42r 2 41 − 55, which has to be compared to condition
4A2 /25x2 + A1 x + A0 where
x2 2 − ç2x V
p S4x5∗ = − xx 0 (22)
r − 4r + 25 − 122 + 42 − 4r + 2552 2N − 1 − 2
A2 = 1
6 We verify that the HJB equation is concave with respect to
1 − S4x5 at the equilibrium for < 42N −15/ and > 42N −15/
A1 = − 1 and
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
Part (b). To obtain the mathematical expression of the < 1/ and ç̃4x5 = 4L2 /25x2 + L1 x + L0 when > 1/, we find
optimal contract depending on the level of risk aversion, we that the globally asymptotic equilibria are characterized by
replace çNx = AN 2 x +AN 1 and Vxx = 4A2N +5/42N −1−5 22 4 −15
in (22) when < 42N −15/, and çNx = BN 2 x +BN 1 and Vxx = K2 = p 1
4 −1544r +25 −r41+ 2 55+ 41+ 2 −54 −15ã
−4BN 2− 5/42N −1−5 in (22) when > 42N −15/, respec-
tively. We find that when < 42N −15/, the optimal contract
41+ 2 54K2 41+ 2 5−5 K2
−1
is S4x5∗ = max803 aN 0 +aN 1 x +aN 2 x2 9, with K1 = r −K2 2 ++ +4 1
1+ 2 − −1
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.
and
+ K12 341 − 5 + 2 43 + 2 2 5
4AN 2 − 54AN 2 + 5
aN 2 = − > 01 −1
· 41 + 2 − 54 − 15 1
241 − 2N + 5
with
and S4x5∗ = bN 0 + bN 1 x + bN 2 x2 , when > 42N − 15/ with
ã = r44 + 4 2 + 25r5 − 2 2 42 + r52 − 122 − 4 2 + 15r 2 1
B 2 + 4 − AN 2 5 BN 1 BN 2
bN 0 = N 1 > 01 bN 1 = > 01 when < 42N − 15/ and
241 − 2N + 5 41 − 2N + 5
L2 = − r41 + 2 5 − 4r + 25
and
4BN 2 − 54BN 2 + 5
p
bN 2 = < 00 + 41 + 2 − 54r 2 41 + 2 5 − 42 − 4r + 252 5
241 − 2N + 5 −1
· 241 + 41 + 5 2 5 1
and S4x5∗ = l0 + l1 x + l2 x2 for the high risk-aversion agent, Hauser JR, Simester D, Wernerfelt B (1994) Customer satisfaction
with incentives. Marketing Sci. 13(4):327–350.
Hauser JR, Simester D, Wernerfelt B (1996) Internal customers and
2 41−5+L2 2 2 +L22 441− 4 5 −41+ 2 52 5 internal suppliers. J. Marketing Res. 33(4):268–280.
l2 = < 01 Holmstrom B (1979) Moral hazard and observability. Bell J. Econom.
241+ 2 −52
10:74–91.
2 +L2 441− 4 5 −41+ 2 52 5 Holmstrom B, Milgrom P (1987) Aggregation and linearity in the
l1 = L 1 1 and provision of intertemporal incentives. Econometrica 55:303–328.
41+ 2 −52
Downloaded from informs.org by [131.91.169.193] on 17 February 2016, at 06:07 . For personal use only, all rights reserved.