Spring 2022

Student Team: Andrew Lai, Edmund Lam, Jinghan Ma, Nicole Neo, Xudan Wang, Yixuan Li
Challenge: Conduct comprehensive customer segmentation analysis using credit card data and present possible insights for marketing purposes.
Problem Statement: To successfully sell a product, knowing the target market and customer needs is key. While traditionally marketers had to rely on customer surveys and companies’ sales figures to understand consumer behavior, now they have access to large-scale data on credit card transactions and consumer demographic traits. The objective of this project was to leverage such data to harness insights that serve to inform more responsive marketing strategies across a myriad of industries.
Envisioned Outcome: The team will produce the following deliverables:
  1. Summary deck of the customer segmentation analysis and insights for marketing strategies;
  2. Visualization of data through a Tableau dashboard that presents the different customer segments and their traits and spending habits
Data: Credit card transaction data from Epsilon (Q3 2019 to Q2 2021); Household-level demographic and Psychographic data from Epsilon
Solution: Using partitional (K-means) and hierarchical (bisecting K-means) clustering algorithms, the team uncovered 2 primary clusters from the transaction data. Then they mapped the transaction data to the demographic and psychographic data to further understand the traits of the clusters. Overall, the analysis found that a majority of consumers (74%) were in Cluster 1 and the minority (26%) were in Cluster 2. Cluster 2 spends more overall compared to Cluster 1, with the biggest difference in spending being on the Supermarket, Other Retail, Restaurants and Home Improvement categories. Cluster 2 comprises more married individuals with children and who have higher purchasing power relative to Cluster 1, and these traits could possibly explain the difference in spending patterns between the two clusters.