UNIT 3 CUSTOMER PROFITABILITY AND ANALYTICS ON

SALES & DISTRIBUTION:

Cluster Analysis, Collaborative Filtering, Classification Trees

for Segmentation. Customer intelligence (CI)for predictive

analytics, Customer Life Time Value (CLTV), How to calculate

CLTV, Customer churn, Metrics for Customer Acquisition and

Retention, Customer Equity, Customer Loyalty, Cohort

analysis, Monte Carlo Simulation and Marketing Decision

making.

Analytics on Sales & Distribution: Metrics for Sales,

profitability, Sales Force Sizing, Effort (call planning),

Territory Planning, Target Setting, Compensation Planning,

Analytics based channel evaluation and selection [6+1]

 CUSTOMER PROFITABILITY ANALYSIS
 Who brings in the most revenue for your company?
 Which customer is costing you the most?
 Are those customers that cost a lot worth it?
 are you wasting your resources catering to shoppers
 who aren’t even bringing considerable profits?
 All these answers (and many more) reveal themselves to you at
the end of a successful Customer Profitability Analysis (CPA).
 Understanding Customer Profitability is an excellent step
toward becoming more profitable in the long term.
 CUSTOMER PROFITABILITY ANALYSIS
 Customer Profitability Analysis (CPA) is finding the
profitability of each customer (or customer segments) by
attributing profits and costs to each separate customer
(respectively, each segment) over a certain period.

 According to the Customer Profitability Analysis definition, CPA

is more of a management accounting tool than a marketing
strategy.
 CUSTOMER PROFITABILITY ANALYSIS
 CPA is a managerial accounting method that allows businesses
to determine the overall profit a customer generates.
 A profitable customer is someone who generates a revenue
stream greater than the cost of their acquisition, selling, and
serving.
 Companies calculate the CPA on a customer level or for the
entire customer group.
 When companies are more focused on products, departments,
and locations of their offices, they often tend to lose focus on the
customers.
 As a result, the companies have to sometimes bear the cost of
maintaining unprofitable customers which is detrimental to their
business.
 CUSTOMER PROFITABILITY ANALYSIS
 CPA allows companies to evaluate their customers and know
how beneficial it is for them to keep the customers.
 Based on this value they can decide upon the cost of serving
them or even to decide whether to continue or let them go.
 It has been found in a study that the size of the customer is not
directly proportional to their profitability.
 Sometimes even the large-sized customers can turn out to be
unprofitable ones for a business.
 CUSTOMER PROFITABILITY ANALYSIS
 To calculate CPA, you need the annual profit per customer, and
the total duration a customer stays with your business.

 Annual profit = (Total revenue generated by the customer in

a year) – (Total expenses incurred to serve the customer in a
year)
 CUSTOMER PROFITABILITY ANALYSIS
 The total revenue can be generated by the following sources that you need to
include:

 Recurring revenue
 Upgrades to the higher plans
 Cross-buying relevant products
 And, expenses can be incurred from the following sources which also you need to
consider:

 Cost of customer service

 Maintaining a customer success team
 Loyalty perks
 Operational cost
 CUSTOMER PROFITABILITY ANALYSIS
 Finally, when you have the annual profit, the customer
profitability analysis calculation goes like this:

 CPA = (Annual profit) x (no. of years customer stays with

company)
 CLUSTER ANALYSIS
 Cluster analysis is a data analysis method that clusters (or groups)
objects that are closely associated within a given data set.
 When performing cluster analysis, we assign characteristics (or
properties) to each group.
 Then we create what we call clusters based on those shared properties.
 Thus, clustering is a process that organizes items into groups
using unsupervised machine learning algorithms.
 Cluster analysis is a useful and straightforward tool for understanding
data patterns.
 The main goal of clustering is to identify the clusters and group them
accordingly.
 USE OF CLUSTER ANALYSIS
 If you have large and unstructured data sets, it can be expensive and
time-consuming to label groups manually. In this case, cluster analysis
provides the best solution to divide your data into groups.
 When you don’t know the number of clusters in advance, cluster analysis
can provide the first insight into groups that are available in your data set.
 When you need to detect outliers in your data, cluster analysis provides an
effective method compared to traditional outlier detection methods, such as
standard deviation.
 Cluster analysis can help you detect anomalies. While outliers are
observations distant from the mean, they don’t necessarily represent
abnormalities. On the other hand, anomalies relate to identifying rare
events or observations that deviate greatly from the mean.
 CLUSTER ANALYSIS IN MARKETING
 When you don’t research and segment your market and customer
base, time and effort may be wasted on product development or
campaigns that simply don’t resonate with your potential
customers.
 The solution includes cluster analysis, an integral part of
identifying both consumer and market segments.
 Cluster analysis is a data analysis technique that identifies
meaningful, naturally occurring groups within a dataset and
distinguishes them as clusters. It is used to discover hidden
relationships in data based on specific characteristics.
 CLUSTER ANALYSIS IN MARKETING
 Can you manually segment your customers and
market? Sure, you can, but the manual method is
limiting and only truly effective with a small
number of characteristics or attributes. It simply
doesn’t scale well. Cluster analysis with advanced
analytics and machine learning can quickly scale to
a high number of attributes. It’s also completely
data-driven, using an unsupervised model (the
algorithm learns patterns without tagged data),
which makes it more accurate and credible.
 CLUSTER ANALYSIS : EXAMPLE
 A company has created what they consider to be
the perfect cocktail dress. They have it priced at $1000.
 They want to target the appropriate market for the dress, so they
know they need to find people who can afford it.
 Traditional segmentation might be based on their belief that only
people over 45 have the income to purchase their dresses.
 But they used clustering and found that younger women of 25-35
not only have the income but are more likely to purchase cocktail
dresses.
 This had a significant impact on their marketing strategy.
 COLLABORATIVE FILTERING
 As a popular approach to e-commerce product recommendations, collaborative
filtering is a technique that can identify similarities between customers on the
basis of their site interactions and then recommend relevant products to
customers across digital properties.
 With collaborative filtering, marketers can tap user data to produce product
recommendations tailored to users’ individual similarities and shopping
behaviors.
 Like a friend who shares your tastes and offers suggestions based on books,
clothes, and brands they love, recommender systems, backed by machine
learning, aim to do the same.
 However, in order to effectively recommend products you might like, the
system must understand who you are
 COLLABORATIVE FILTERING
 A popular approach to product recommendations, collaborative
filtering is a type of personalized recommendation strategy that
identifies the similarities between users (based on site interactions)
to serve relevant product recommendations across digital properties.
 Recommender systems collect user information, mining this data to
inform which items to display.
 The data includes, but is not limited to:
 Which products a user has viewed
 Which products a user has clicked on
 Which products a user has searched for
 Which products a user has added to their cart
 Which products a user has purchased before
 COLLABORATIVE FILTERING
 Analyzing these massive datasets based on a site visitor’s behavior and activity,
the system analyzes product attributes listed in data feeds to begin crafting
predictions, serving product recommendations across any page of a site to drive
a customer closer to a purchase.
 To effectively do so, the system taps two different types of data:
 Explicit data: Data a user actively provides, such as answers to a questionnaire
or survey
 Implicit data: Data inferred by a system based on a user’s behavior, such as a
preference for sneakers after viewing several pairs and purchasing two pairs in
the last six months
EXAMPLES OF COLLABORATIVE FILTERING APPLICATIONS

 Amazon uses CF to match products to customers based on their

past purchases.
 While the world was focusing on user-based collaborative
filtering, Amazon came up with a new algorithm called item-
based (or item-to-item) collaborative filtering in 1998.
 With this item-based collaborative filtering algorithm, product
recommendations are created not just based on similarities
between customers but also on correlations between
products/items.
 EXAMPLES OF COLLABORATIVE FILTERING APPLICATIONS

 Netflix is known for using collaborative filtering to

build its movie recommendation system 🎬. Here’s
an example of how Netflix applies used-based CF to
make a movie recommendation (Movie C) to User A: