juniorcl/health-insurance-cross-sell
data science project to improve cross selling through consumer ranking.
Builds a propensity-scoring classifier using Logistic Regression to rank 127K customers by likelihood of purchasing health insurance, enabling the sales team to prioritize 20K outbound calls toward highest-probability prospects. The pipeline implements feature engineering via hypothesis testing, dimensionality reduction with Boruta algorithm, and k-fold cross-validation across multiple baseline models (Random Forest, XGBoost, LightGBM) before hyperparameter tuning. Deploys the trained model via Flask API for integration into existing sales workflows.
No commits in the last 6 months.
Stars
8
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 04, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/juniorcl/health-insurance-cross-sell"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Elsemary/Actuarial-Reserve-Risk-Classification-with-Gaussian-Mixture
Classification of reserve risk with chain-ladder
burning-cost/burning-cost.github.io
Burning Cost blog and course landing page — open-source insurance pricing tools for UK actuarial...
burning-cost/bayesian-pricing
Hierarchical Bayesian models for insurance pricing — PyMC 5, thin-data segments, credibility factors
burning-cost/insurance-distill
GBM-to-GLM distillation for insurance pricing - surrogate factor tables for Radar/Emblem rating engines
Symfa-Inc/insurance-pricing
Transparent AI for insurance pricing: Predicts premiums and explains "why" using SHAP and...