Predicting Daily Road Collisions with Weather, Calendars & Machine Learning

End-to-end analytics project comparing interpretable linear regression with a deep neural network to forecast daily road collision risk using calendar and weather signals.

Problem

Urban transport authorities and emergency services require reliable indicators to anticipate periods of elevated road risk. This project explores whether daily collision counts can be predicted using a combination of calendar behaviour patterns and weather conditions.

Three key questions guided the analysis:

Data

Daily collision records were joined with weather observations to create a unified dataset suitable for exploratory analysis and predictive modelling.

Feature Engineering

Exploratory Insights

The findings suggest behavioural patterns such as commuting activity dominate collision frequency, while weather conditions act as secondary modifiers.

Modelling Approach

Two modelling strategies were evaluated.

The neural network architecture used two hidden layers with ReLU activation, trained using the Adam optimiser and MAE loss.

Model Performance

Linear Model (Day Only)
MAE ≈ 0.144
Linear Model (Day + Weather)
MAE ≈ 0.127
Deep Neural Network
MAE ≈ 0.123

The neural network provides a modest improvement by capturing interactions between weekday behaviour and weather conditions.

Key Insight

Weekly behavioural patterns are the dominant driver of collision frequency. Weather conditions refine the prediction but do not fundamentally alter the risk structure. For example, weekend days consistently show lower predicted collision counts compared with mid-week commuting days, even under similar temperature conditions.

Applications

Ethics & Limitations

Project Links