Machine Learning
Customer Churn Prediction
Telecom churn with retention insights.
Project overview
Customer Churn Prediction is a mentor-guided ML project designed for university submission. Classify likely churn customers and highlight top contributing features for retention strategy discussions. The build uses Python, XGBoost, Pandas, Streamlit and is structured so you can explain architecture, modules, and test cases during viva. Typical delivery timeline is 6–8 weeks depending on package and college deadlines.
Best suited for: Students working on predictive analytics and applied ML projects
Tech stack
Objectives
- Design and implement a working solution for “Customer Churn Prediction” aligned to academic evaluation criteria.
- Demonstrate core features such as Churn score, Feature importance, Dashboard.
- Produce documentation (synopsis, report chapters, and PPT) suitable for guide approval.
- Prepare viva-ready explanations for design choices, tech stack, and future enhancements.
Key modules
- Module: Churn score
- Module: Feature importance
- Module: Dashboard
- Documentation, deployment notes, and viva Q&A
Key features
- Churn score
- Feature importance
- Dashboard
- CSV upload
Deliverables
- Notebook
- Dashboard
- Report
- PPT
- Viva pack
Learning outcomes
- Runnable source code with setup guide
- University-style report draft
- Presentation deck (PPT)
- Mentor review checkpoints
