Analytical CRM

Analytical CRM
 Analytical CRM is a subset of CRM in which data is collected
by a company about their customer interactions, with the goal of
increasing customer satisfaction and their customer
retention rate.

 Analytical CRM is a behind-the-scenes process; the customer is

not aware that his or her actions and interactions with the
company are being captured and analyzed.

 Based on the information gathered about customer practices,

interactions and the end results of these interactions, companies
can predict customer trends and suggest products towards which
the customer is most likely to gravitate.
 A company like Amazon might use technology to capture
data about customer preferences, including what the
customer purchased, the length of time he or she reviewed
an item, and how much favorability he or she expressed
towards the items. This would help Amazon identify
customer trends, likes and dislikes.

 Then based on this information, the company can create

targeted customer marketing strategies, such as offering
promotions on items the customer has previously
purchased, and presenting the customer with items similar
to things that he or she has recently browsed on their
website.
 Benefits of Analytical CRM

Account Based Marketing

Marketing Campaign Optimization
Knowledge on what motivates prospects to
become customers
New sales opportunities
It helps in cross selling, up selling
It helps in market basket analysis
 How to begin using analytical CRM

 Track every interaction with your web pages, emails, and

content types, such as video views and whitepaper
downloads.

 Look for patterns of people that have eventually bought and

work your way backwards to focus on those demonstrating
a similar buying progression. For instance, if 10% of the
clients who have downloaded a white paper also signed up
for your blog became buyers of your product, this
behavioral segment becomes a hot lead list that your sales
reps can target.
 Apply scores to different digital behaviors that demonstrate
purchase intent, and then rank your leads accordingly. For
example, a “video view” may be scored as three points
whereas a “meeting request” could warrant ten points.‍

 Use data appending tools to gather as much info on the

interested companies as possible to reduce sales research
time (e.g. email addresses, coworkers, company revenue,
addresses, phone numbers, and social media accounts).
Much of this information is available through built-in
analytic CRM tools and the info can be appended to your
CRM.
 Importance of Data Mining
Data Mining: Data mining is the process of sorting through
large data sets to identify patterns and establish relationships to
solve problems through data analysis. Data mining tools allow
enterprises to predict future trends.

 Data mining is the process of unearthing useful patterns

and relationships in large volumes of data. A sophisticated
data search capability that uses statistical algorithms to
uncover patterns and correlations, data mining extracts
knowledge buried in corporate data warehouses.
 Market-Basket Analysis
Market Basket Analysis is a modelling technique
based upon the theory that if you buy a certain group
of items, you are more (or less) likely to buy another
group of items.

For example, if you are in an English pub and you

buy a pint of beer and don't buy a bar meal, you are
more likely to buy chips at the same time than
somebody who didn't buy beer.
 The set of items a customer buys is referred to as an
itemset, and market basket analysis seeks to find
relationships between purchases.

 Typically the relationship will be in the form of a rule:

 IF {beer, no bar meal} THEN {crisps}.

 The probability that a customer will buy beer without a bar

meal (i.e. that the antecedent is true) is referred to as the
support for the rule. The conditional probability that a
customer will purchase crisps is referred to as the
confidence.
 Association Rules are widely used to analyze retail basket or
transaction data, and are intended to identify strong rules
discovered in transaction data using measures of
interestingness, based on the concept of strong rules.

 Association Rule Mining is used when you want to find an

association between different objects in a set, find frequent
patterns in a transaction database, relational databases or
any other information repository.
 The most common approach to find these patterns is
Market Basket Analysis, which is a key technique used by
large retailers like Amazon, Flipkart, etc to analyze
customer buying habits by finding associations between the
different items that customers place in their “shopping
baskets”.

 The discovery of these associations can help retailers

develop marketing strategies by gaining insight into which
items are frequently purchased together by customers.
Difference between Association and Recommendation
 How it is used?
 In retailing, most purchases are bought on impulse. Market basket
analysis gives clues as to what a customer might have bought if the idea
had occurred to them.

 As a first step, therefore, market basket analysis can be used in deciding

the location and promotion of goods inside a store.

 If, as has been observed, purchasers of Barbie dolls have are more likely
to buy candy, then high-margin candy can be placed near to the Barbie
doll display. Customers who would have bought candy with their Barbie
dolls had they thought of it will now be suitably tempted.
Application Areas of Market Basket Analysis

Analysis of credit card purchases.

Analysis of telephone calling patterns.
Identification of fraudulent medical insurance
claims.
(Consider cases where common rules are broken).
Analysis of telecom service purchases.
 Retail. In Retail, Market Basket Analysis can help determine what
items are purchased together, purchased sequentially, and purchased
by season. This can assist retailers to determine product placement and
promotion optimization (for instance, combining product incentives).
Does it make sense to sell soda and chips or soda and crackers?

 Telecommunications. In Telecommunications, where high churn

rates continue to be a growing concern, Market Basket Analysis can be
used to determine what services are being utilized and what packages
customers are purchasing. They can use that knowledge to direct
marketing efforts at customers who are more likely to follow the same
path. For instance, Telecommunications these days is also offering TV
and Internet.
Creating bundles for purchases can be determined from an analysis of
what customers purchase, thereby giving the company an idea of how to
price the bundles. This analysis might also lead to determining the
capacity requirements.
 Banks. In Financial (banking for instance), Market Basket
Analysis can be used to analyze credit card purchases of
customers to build profiles for fraud detection purposes and
cross-selling opportunities.

 Insurance. In Insurance, Market Basket Analysis can be used to

build profiles to detect medical insurance claim fraud. By
building profiles of claims, you are able to then use the profiles
to determine if more than 1 claim belongs to a particular claimee
within a specified period of time.
 Customer profiling

Decision about which data will or will not have to

gathered and maintained should not be made on ad-
hoc basis. An ideal customer profile will have to form
the foundation, which is indispensable to being able
to implement the planned relationship policy.

Company usually choose not to keep all of the raw

data but instead to revise them so that a better and
more easily maintained customer profile develops.
 Customer Profile
Aspects Characteristics

Segment In which segment consumer should be placed

Customer Value Annual turnover, contribution to profit, life time value

Transactions Payment behavior, Method of payment, Description of the

purchases

Products Which products has the customer purchased, in which

quantities and at which time, when does warranty expires

Communication Address use to login, page consumer use to enter the site,
through the duration of visit
internet/telephone
Customer Type of residence, type of city, composition of household,
Characteristics income, education, socio-economic class

Satisfaction Customer satisfaction with products, services,

communication.
 RFM Analysis

RFM analysis is a customer segmentation technique that uses

past purchase behavior to divide customers into groups.

RECENCY (R): Time since last purchase

FREQUENCY (F): Total number of purchases
MONETARY VALUE (M): Total monetary value

First used by the direct mail industry more than four

decades ago, yet it is still an effective way to optimize
your marketing.
 Benefits of RFM Analysis

Increased customer retention

Increased response rate
Increased conversion rate
Increased revenue
 RFM factors illustrate these facts:

The more recent the purchase, the more responsive the

customer is to promotions.

The more frequently the customer buys, the more engaged

and satisfied they are

Monetary value differentiates heavy spenders from low-

value purchasers
 Customer Segments- RFM model
Customer
Activity Actionable Tip
Segment
Reward them. Can be early
Bought recently, buy often
Champions adopters for new products.
and spend the most!
Will promote your brand.
Spend good money with us
Upsell higher value products.
Loyal Customers often. Responsive to
Ask for reviews. Engage them.
promotions.
Recent customers, but Offer membership / loyalty
Potential Loyalist spent a good amount and program, recommend other
bought more than once. products.

Provide on-boarding support,

Recent Bought most recently, but
give them early success, start
Customers not often.
building relationship.
 Recent shoppers, but haven’t spent Create brand awareness, offer
Promising
much. free trials

Customers Above average recency, frequency Make limited time offers,

Needing and monetary values. May not have Recommend based on past
Attention bought very recently though. purchases. Reactivate them.

Share valuable resources,

Below average recency, frequency
recommend popular products /
About To Sleep and monetary values. Will lose
renewals at discount, reconnect
them if not reactivated.
with them.

Spent big money and purchased Send personalized emails to

At Risk often. But long time ago. Need to reconnect, offer renewals,
bring them back! provide helpful resources.

Made biggest purchases, and often. Win them back via renewals or
Can’t Lose Them But haven’t returned for a long newer products, don’t lose them
time. to competition, talk to them

Lowest recency, frequency and Revive interest with reach out

Lost
monetary scores. campaign, ignore otherwise.
RFM Analysis Question
 Assumptions

Recency- 1-4=5, 5-10=4, 11-25=3, 26-40-2, 40 and

above=1

Frequency- 10 & above=5, 7-9=4, 5-4=3, 3-2=2,

1=1

Monetary Value: 800 & above=5, 650-799=4,

500-649=3, 300-499=2, below 300=1
RFM scores
 Data Sources
Internal: company own records.

External: these are services providers that setup

database containing characteristics of natural
persons and legal entities. Data from these databases
may be rented or purchased for the purposes of
enriching one’s own customer database.
 Segmentation criteria

Segmentation criteria are used to divide up the consumer market

such as:

 Geographical characteristics
 Demographic characteristics
 Socio economic data such as income, education, social class.
 Behavior such as purchase or communication behavior
 Psychographic characteristics such as lifestyle, set of norms and
values
Segmentation criteria are used to divide up the business market
such as:

 Demographic factors including industrial classification, company

size and location.
 Operating variable such as technology, user status, customer
capabilities.
 Purchasing approaches which describe how purchasing is
organized.
 Situational factors: urgency, order size etc.
 Segmentation Guidelines

Measurable
Substantial
Accessible
Differentiable
Actionable