TRAVEL & HOSPITALIY
Customer Segmentation and Cross-Sell Modeling for a Leading Indian Online Travel Portal
C U S T O M E R
S E G M E N T A T I O N
& C R O S S – S E L L
M O D E L
T E C H N O L O G Y
ETL – Hadoop
Data warehouse – Amazon
Redshift
Reporting – Ideata
Models – Clustering model,
Predictive model
O B J E C T I V E
Improve customer engagement by increasing frequency of
repeat booking and cross-sell of products from other verticals.
A P P R O A C H
Analyzed transactions spanning six LOBs with over 200+
million records.
Identified four major customer segments using K-Mean
clustering based on value and travel behavior.
Created business rules based on customer behavior to
identify personal, family and business travelers and to
classify customers by their affluence level.
Developed a predictive cross-sell model to identify top 30%
of most recent travelers who can be targeted with hotel
offers.
Executed email campaign using test & control groups to
cross-sell hotels.
O U T C O M E
Higher conversion of customers targeted with offer as
compared to control group for hotel bookings immediately
post campaign.