Data Mining and Visualization to Understand Accident-prone Areas

TL;DR

This paper combines data mining and visualization methods to identify accident-prone areas and times, providing insights that can aid policymakers and law enforcement in accident prevention.

Contribution

It introduces an integrated approach using data mining and visualization to analyze accident patterns and evaluates visualization techniques for non-expert understanding.

Findings

Most accidents occur between 6-7 pm at dusk.

Friday is the most accident-prone day.

October has the highest number of accidents.

Abstract

In this study, we present both data mining and information visualization techniques to identify accident-prone areas, most accident-prone time, day, and month. Also, we surveyed among volunteers to understand which visualization techniques help non-expert users to understand the findings better. Findings of this study suggest that most accidents occur in the dusk (i.e., between 6 to 7 pm), and on Fridays. Results also suggest that most accidents occurred in October, which is a popular month for tourism. These findings are consistent with social information and can help policymakers, residents, tourists, and other law enforcement agencies. This study can be extended to draw broader implications.