Accident Severity Detection Using Machine Learning


  • Nagma Bi Student, Department of Computer Science & Engineering, Integral University, INDIA
  • Dr. Halima Sadia Associate Professor, Department of Computer Science & Engineering, Integral University, INDIA



Decision tree (DT), K- Nearest Neighbour (KNN), Random Forest (RF), Gradient Boosting Classifiers (GBC)


Road accidents are one of the most regrettable hazards in this hectic world. Each year, traffic accidents cause a large number of casualties, illnesses, and deaths in addition to suffering huge financial losses.There are numerous things that cause traffic accidents, especially those related to the environment, vehicles and the travelers.By analyzing the severity of the road accidents that happened in the past, and the factors that caused it, it is possible to take precautionary measures to reduce the road accidents rate significantly in the future.This project includes developing a machine learning model that can categorize accident severity depending on the circumstances that affected the accident. A prediction model was created using a variety of machine learning classifiers, including Gradient Boosting Classifiers (GBC), K-Nearest Neighbour (KNN), Random Forest (RF), and Decision Tree (DT). The severity of a road accident can be detected 90% accurately, according to the results of a gradient boosting algorithm.The study makes use of publicly accessible European data.The approach presented in the research is broad enough to be used with various data sets from other nations.Additionally, the web portal's model was used to create an intelligent system for predicting the severity of accidents.


Download data is not yet available.



How to Cite

Nagma Bi, & Dr. Halima Sadia. (2023). Accident Severity Detection Using Machine Learning. International Journal of Engineering and Management Research, 13(3), 203–208.