Traffic volume, geographic centrality and unique relief have led to an increase in traffic accidents and fatalities every year since 2015. The Chattanooga Smart Community Collaborative (CCSC), launched the ’911 Project – Predicting Hotspots for Accidents’ in early 2018. It uses machine learning, specifically multi-layer perceptron (MLP) neural network models, to analyse both historic and current 911 data to identify accident trends. This dataset is cross-referenced with DarkSky weather data, roadway geometric data and accident time, date, geographical coordinates. The dataset is then used to create a visualisation of accident ’hotspots’ within a virtual grid of Chattanooga helping to determine traffic strategies.
