dnkirill/allstate_capstone

Allstate Kaggle Competition ML Capstone Project

39
/ 100
Emerging

Implements an end-to-end regression pipeline combining XGBoost and Keras neural networks with hyperparameter tuning via Hyperopt, then stacks predictions using linear regression for improved accuracy. Structured as four Jupyter notebooks covering exploratory data analysis, individual model optimization with K-Fold cross-validation, and ensemble validation. Includes deployment scripts for AWS EC2 instances (CPU and GPU variants) and supports both pretrained models for quick evaluation and from-scratch training workflows.

No commits in the last 6 months.

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.