A comprehensive exploration of San Francisco crime data using machine learning techniques, focusing on the Histogram-Based Gradient Boosting Classifier. This project was inspired by the Kaggle competition.
This repository presents an end-to-end pipeline for analyzing and predicting crime categories in San Francisco based on historical data. It leverages machine learning, data visualization, and feature engineering to build an effective predictive model.
Read the detailed write-up of this project on Medium:
Unmasking San Francisco's Underworld: Solving Crimes with HistGradient Classifier