dnkirill/allstate_capstone

Allstate Kaggle Competition ML Capstone Project

39
/ 100
Emerging

This project offers a sample solution for actuaries or insurance claims analysts looking to accurately predict the severity of auto insurance claims. By taking raw claims data, it walks through how to train and optimize two distinct machine learning models (XGBoost and Multilayer Perceptron) and then combine their predictions for a more robust outcome. This process yields a final, more precise claims severity prediction.

No commits in the last 6 months.

Use this if you are an actuary or insurance analyst who needs to understand how to build, optimize, and combine machine learning models to predict the financial impact of insurance claims.

Not ideal if you are looking for a plug-and-play tool for immediate deployment, as this project serves more as an educational guide and framework for model development rather than a production-ready system.

insurance-claims-prediction actuarial-science risk-assessment claims-severity-modeling machine-learning-workflow
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 22 / 25

How are scores calculated?

Stars

82

Forks

57

Language

Jupyter Notebook

License

Last pushed

Dec 10, 2016

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dnkirill/allstate_capstone"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.