Customer Churn InsightLab
A churn analytics workbook and dashboard pipeline for exploring drivers of customer attrition, segmenting at-risk users, and quantifying retention lift.
- Python
- Pandas
- Classification
- Retention
Role
Feature engineering, modeling, insight communication
Timeframe
2025
The problem
Teams know their churn rate but rarely know which behaviors precede it, or which at-risk segment is worth spending retention budget on.
Approach
- 01
Profiled customer activity, billing, and support data to build behavioral features ahead of the churn window.
- 02
Trained interpretable classification models and ranked drivers by contribution.
- 03
Segmented customers into risk tiers and sized the revenue exposure of each tier.
- 04
Packaged the analysis into a repeatable workbook plus dashboard pipeline.
Outcome
A ranked list of churn drivers stakeholders can act on rather than a single accuracy figure.
Risk tiers with attached revenue exposure, so retention effort can be prioritized.
A rerunnable pipeline that refreshes as new periods land.
More case studies
SaaS Retention Warehouse
A full analytics warehouse for SaaS revenue and retention. Built a star schema in DuckDB, modeled cohort retention, MRR waterfall, NRR, and LTV, and served metrics through a FastAPI + React dashboard.
Readmit-IQ
End-to-end ML system for hospital readmission risk. PySpark medallion architecture, scikit-learn modeling with SHAP explainability, FastAPI inference, and a React frontend with RAG over PubMed via Qdrant.
Surgical Complications Benchmarking
Multi-page Streamlit dashboard benchmarking real CMS hospital surgical outcomes. Includes a calibrated synthetic patient-level layer for risk adjustment and predictive modeling.