GIS-Integrated Machine Learning Framework for Predicting Traffic Accident Hotspots: A Spatial Analysis Approach
GIS-Integrated Machine Learning Framework for Predicting Traffic Accident Hotspots: A Spatial Analysis Approach

Summary/Abstract: In city areas such as Metro Manila, Philippines, traffic accidents are the largest threat to urban growth and public safety. The K-Nearest Neighbors (KNN) method is used in this study's machine learning and GIS-based technique to predict the sites of traffic incidents. Based on spatial data and historical accident records, it integrates geographic and contextual factors to generate risk maps that identify locations likely to be accident-prone. There was room for improvement, as the predictive model had a 97% accuracy rate with good precision, but a somewhat lower recall. Urban planning initiatives, resource allocation, and traffic control methods can all benefit from the practical insights that GIS-based visualizations offer. Thus, the method suggests that combining machine learning and spatial analytics could improve road safety.

• Details
• Contents