Big Data Analytics: Volvo Case Study
- Paulina y
- Jun 25, 2025
- 1 min read
Situation:
Volvo, aiming to improve its car sales strategy and market positioning, needed to understand how different customer segments behave, especially in relation to financing options and car model preferences. The task was to analyze the Volvo dataset using data mining techniques to support targeted marketing and decision-making.
Task:
As a business analyst student, my goal was to segment customers effectively, determine which financing options influenced car purchases, and identify which car models (e.g., S90, XC60, XC90) should be promoted online. I applied the CRISP-DM framework and used tools like WEKA to carry out clustering and association rule mining.
Action:
I prepared the dataset by converting numerical attributes to nominal ones for compatibility with data mining algorithms. I used the CFsSubsetEval method to select key attributes (ID and financing), applied KMeans clustering to identify customer segments, and conducted Apriori association rule analysis to discover patterns between financing use and car purchases. I also evaluated cluster characteristics to derive insights for marketing strategies.
Result:
Identified 4 customer clusters, each with distinct behaviors and preferences.
Discovered that financing options strongly influence purchase decisions (confidence = 1.0; lift = 1.64).
Found that Volvo S90 and XC60 are ideal models for online promotion due to consistent interest across customer segments.
Proposed that targeted financing deals could boost conversions and drive showroom traffic, directly supporting marketing strategy optimization.
