← Back to projects

Customer-Churn Prediction

Developed a customer churn prediction system using data preprocessing, feature engineering, and machine learning models to identify at-risk customers and support retention strategies.

Timeline
Apr 2024 – jul 2024
Role
Undergraduate Researcher
Stack
python, c++, ml
Contributions
feature engineering, model building, and evaluation to identify at-risk customers.

Approach

  • Data collection: Gathered and consolidated customer data from multiple sources
  • Data preprocessing: Cleaned, handled missing values, and prepared data for analysis.
  • Feature engineering: Created meaningful features to capture customer behavior.
  • Model development: Trained and tuned machine learning models for churn prediction.
  • Model evaluation: Assessed performance using metrics to ensure accuracy and reliability.

Highlights

  • Improved customer retention insights.
  • Built ML model achieving ~87% accuracy.
  • Improved prediction performance by ~15% .