Predictive Analysis of Road Accidents in India: A Machine Learning Approach

Manjunatha, Harini (2023) Predictive Analysis of Road Accidents in India: A Machine Learning Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

The road traffic accident in India poses serious threat as it impose huge socioeconomic costs on a society. The increased numbers in fatalities and injuries due to road accident has forced government to look for solutions to reduce the accident rate. Predicting road accidents is crucial because it helps avoid fatalities, reduce injuries, and allocate resources effectively. Recognising locations and times when accidents are likely to occur allows authority to respond quickly, allowing for traffic control measures and the development of safer infrastructure designs. This project focuses on the development and application of machine learning algorithms for road accident prediction. Multiple machine learning(ML) models, including Random Forest, linear regression and Decision Trees were used and thoroughly analysed to assess how accurately they predicted the possibility of an accident. The Random Forest Regressor model demonstrated superior performance comparatively by predicting accidents on road based on historical patterns. The analysis of the models predictions showed that accidents peaked frequently in different parts of India between the time period of 15:00 to 21:00. The time period with the fewest accidents occurred during the night, specifically between 3 AM and 6 AM. Madhya Pradesh experiences the highest accident rate among all states in India, while Lakshadweep exhibits the lowest accident rate among them. The model’s findings can significantly improve traveller safety and aid authorities in developing plans to reduce and eliminate fatal accidents on Indian roads.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Subhnil, Shubham UNSPECIFIED
Uncontrolled Keywords:	Road accident; Machine learning; Fatalities; Time interval
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TL Motor vehicles. Aeronautics. Astronautics Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	16 May 2025 10:51
Last Modified:	16 May 2025 10:51
URI:	https://norma.ncirl.ie/id/eprint/7566

Actions (login required)

View Item