Road Safety Predictor

Applied Machine Learning module at BUas, Year 1 Block D. Client-facing group project for the municipality of Breda.

Machine learning system predicting road accident risk levels (low / medium / high) for Breda. Merges the ANWB Safe Driving Dataset with six years of Breda accident records, trains ensemble and neural-network models, and deploys via Streamlit.

Key Highlights

01.Merged ANWB Safe Driving Dataset with Breda Accident Data 2017–2023 into a unified training corpus.
02.Applied SMOTE oversampling to balance low/medium/high risk classes alongside feature engineering and outlier removal.
03.Evaluated Neural Networks, Decision Trees, Random Forests, and Gradient Boosting via k-fold cross-validation.
04.Deployed final model as a Streamlit web application; designed a Google Maps overlay concept in Figma.
05.Classified as High Risk under the EU AI Act, with documented compliance for Articles 10, 12, and 13.