C5i Case Studies Customer Segmentation for a Leading Money Exchange Company

Edit This Case Study Record

	Customer Segmentation for a Leading Money Exchange Company C5i

Customer Segmentation for a Leading Money Exchange Company

C5i

Technology Category	Analytics & Modeling - Predictive Analytics
Applicable Industries	Finance & Insurance
Applicable Functions	Sales & Marketing
Services	Data Science Services
Challenge	The company wanted to segment its customers according to their transaction patterns and other behavioral traits in order to identify the profitable customers and target relevant ones for the loyalty program. They also wanted to identify the customers performing adversely as compared to the cluster average and timely target them for reactivation. The goal was to perform targeted campaigns based on the behavioral pattern of the customers for revenue maximization. Read More
About Customer	The customer is a leading money exchange company operating globally. They are one of the world's top companies in the financial services industry. The company wanted to understand their customers better for targeted promotions and reactivation campaigns. They aimed to identify profitable customers and target relevant ones for their loyalty program. Additionally, they wanted to identify customers performing adversely compared to the cluster average and target them for reactivation timely. The ultimate goal was to perform targeted campaigns based on the behavioral pattern of the customers for revenue maximization. Read More
Solution	The solution involved perceiving customer behavior through the analysis of their transactional trends. RFM (Recency, frequency, monetary) variables were used to perform K-means clustering to congregate similar characteristics and segregate dissimilar trends. Two models were built, one at an overall business level and the other at corridor level to have a better understanding of customers in different countries. Profiling of the customers in different clusters was done based on their transaction pattern (salary, festival, campaign period etc.). Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Predictive Analytics

Applicable Industries

Finance & Insurance

Applicable Functions

Sales & Marketing

Services

Data Science Services

Challenge

The company wanted to segment its customers according to their transaction patterns and other behavioral traits in order to identify the profitable customers and target relevant ones for the loyalty program. They also wanted to identify the customers performing adversely as compared to the cluster average and timely target them for reactivation. The goal was to perform targeted campaigns based on the behavioral pattern of the customers for revenue maximization.

About Customer

The customer is a leading money exchange company operating globally. They are one of the world's top companies in the financial services industry. The company wanted to understand their customers better for targeted promotions and reactivation campaigns. They aimed to identify profitable customers and target relevant ones for their loyalty program. Additionally, they wanted to identify customers performing adversely compared to the cluster average and target them for reactivation timely. The ultimate goal was to perform targeted campaigns based on the behavioral pattern of the customers for revenue maximization.

Solution

The solution involved perceiving customer behavior through the analysis of their transactional trends. RFM (Recency, frequency, monetary) variables were used to perform K-means clustering to congregate similar characteristics and segregate dissimilar trends. Two models were built, one at an overall business level and the other at corridor level to have a better understanding of customers in different countries. Profiling of the customers in different clusters was done based on their transaction pattern (salary, festival, campaign period etc.).

Impact #1	The model led to grouping of customers into five different clusters for customers who were doing multiple transactions.
Impact #2	New customers or customers who did just one transaction were grouped basis whether they made a transaction during salary week, festive season or promotional campaigns.
Impact #3	The segmentation helped the client to understand their customers better.

Impact #1

The model led to grouping of customers into five different clusters for customers who were doing multiple transactions.

Impact #2

New customers or customers who did just one transaction were grouped basis whether they made a transaction during salary week, festive season or promotional campaigns.

Impact #3

The segmentation helped the client to understand their customers better.

Download PDF Version

Overview

Customer Segmentation for a Leading Money Exchange Company

Operational Impact