-
Mapped key decision factors influencing credit card adoption
-
Identified customer profiles most likely to convert for each card type
-
Optimised marketing efforts through data-driven targeting
CLIENT CHALLENGES
- A US-based consumer credit firm approached us to understand the thought process behind a customer’s decision to apply for different types of credit cards
- The client wanted to analyse survey data to determine which customer traits influence decisions to opt for student, cashback, travel or premium cards
- The goal was to segment the customer base and enhance conversion rates through targeted marketing
OUR APPROACH
- Step 1: Data collection
-
We conducted a structured survey dataset from 5,000 respondents covering the following:
-
Demographics (age, income, student status)
-
Behavioural traits (online activity, response to offers)
-
Channel interaction (email/SMS/phone)
-
Product preference across four card types
-
-
- Step 2: Decision tree modelling
-
We used a classification and regression tree (CART) model to do the following:
-
Predict the most likely credit card type a customer would apply for
-
Understand the hierarchical influence of various features
-
Map the sequential logic of customer decisions
-
-
- Step 3: Segmentation analysis
-
Used Gini Index to split decision nodes and identify the most important variables
-
Mapped customer journeys to interpretable decision rules
-
Validated findings against actual conversion outcomes from past campaign data
-
IMPACT DELIVERED
- Create targeted campaigns by age, income and credit score brackets
- Optimise email-based marketing for high-response segments
- Increase cashback card conversions by 18% through segment-specific messaging
- Identify that 42% of potential applicants favoured a cashback offering under specific thresholds

Thank you for sharing your details
Your file will start downloading automatically
If it does not download within 1 minute,