Maximized customers’ lifetime values for a Fortune 100 financial services company

Our client, a Fortune 100 financial services company, specializes in payment card services and wanted to maximize revenue from its existing corporate
customers and improve their overall Customer Lifetime Values (CLV).

TransOrg implemented several customer analytics-based solutions using top machine learning and advanced analytics techniques and:

• Identified affluent corporate customers to target with upsell and cross-sell campaigns
• Identified card members for a potential premium card upgrade

TransOrg stitched past 12 months data from multiple sources that included:

• Personal data such as customers’ demographics, credit bureau information, income, sources of income
• Transactional data such as payments history, transaction frequency, transaction size, transaction category, customer engagement level with different merchant categories

Data was categorized, cleaned, and transformed for an exploratory analysis conducted in two phases:

Phase 1: Segmented customers based on overseas transaction behavior

TransOrg analyzed data on customers’ overseas transactions to capture the variation, repeatability, ticket size of a transaction, engagement level of the customer transacting at certain merchant categories and persistency of transactions at customer level.

Secondary variables, such as cash conversion cycles and customers’ forex need, were evaluated and layered with bureau scores.

Customer segments were created based on customers’ monetary values and persistency. Customers in highly valuable segments were targeted with upsell and cross-sell campaigns while customers in lower segments were targeted with engagement campaigns.

Phase 2: Identified card members for a potential premium card upgrade

TransOrg targeted customers with high spending cards per year or cards availing premium benefits such as travel based benefits by paying additional charges.

To segregate such cards, TransOrg analyzed variables such as:

• Overall spend
• Spend on air and lodging
• International travel count
• First class or business class travel count
• Average lodging spend

Based on insights, TransOrg divided the customers into clusters using K-means clustering technique. Customers in the cluster with highest spending cards were chosen for potential card upgrade campaigns resulting in higher revenues for the client and better customer experience.

Maximized customer lifetime values
By targeting cross-sell campaigns to customers in high value segments and improving engagement with customers in low value segments

Improved customer acquisition
Identified attributes of high value and loyal customers to improve criteria for selecting and acquiring new and prospective customers

Increased revenues
Besides improving customer engagement, direct positive impact on topline revenues from both high value and low value customer segments