Upsell/Cross-sell Conversion

The Challenge

The challenge is to improve the upsell/cross-sell conversion rates from historical transaction patterns. Traditional methods require significant hand-crafted feature engineering.
Target customers should be identified accurately for cross-selling a product and increase the sales conversion ratio.

What we do


  • Automated the process of identifying and segmenting customers financial behavior
  • Derived micro segments based on customer behavior and insights into micro segments


The challenge here is to use historical transactional data and patterns to understand the customer’s propensity to buy a new product. The traditional approach involved segmenting customers based on demographics.

  • Multilayer deep learning network to analyze financial transactions and identify behavioral patterns
  • Segment behavioral patterns using auto-naming clustering techniques
  • Estimate the propensity of the customer to buy a product


  • Explainable actionable insights to sales representatives enabling them to meet targets in quick time
  • Increased the lift in the top 3 deciles (15-55% spread throughout)