Road Traffic Accident Severity Prediction Using Machine Learning
INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 11.04.2026 · 10 (04) · 1-9
DOI: 10.55041/ijsrem59437 ↗Kurz gefasst
Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 11.04.2026. Verfasst von Durgeshwari Sahu und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Road traffic accidents are a major public safety concern worldwide, particularly in developing countries such as India, where rapid urbanization, increasing vehicle density, and inadequate road infrastructure significantly contribute to accident rates. Predicting accident severity in advance can help authorities implement preventive measures, improve emergency response systems, and reduce fatalities and injuries. In this work, an approach is developed to predict road traffic accident severity using key environmental and traffic-related parameters such as weather conditions, road condition, visibility, vehicle speed, and time of day. A synthetic dataset containing 50,000 records was generated to simulate realistic accident scenarios due to the limited availability of structured real-world datasets in India. Multiple machine learning algorithms, including Support Vector Machine (SVM), Random Forest, XGBoost, and Artificial Neural Network (ANN), were implemented and evaluated to analyse their performance. The models were trained and tested using preprocessing techniques such as feature scaling and train-test splitting. Performance evaluation was carried out using classification accuracy and confusion matrix analysis. The results show that ensemble learning models, particularly XGBoost, achieve higher accuracy compared to traditional machine learning models due to their ability to handle nonlinear relationships and reduce overfitting. The analysis shows that machine learning techniques are useful in predicting accident severity and identifying high-risk conditions. This work contributes to the development of intelligent transportation systems by providing a scalable and data-driven solution for accident prediction. The developed model can assist traffic management authorities, policymakers, and emergency services in improving road safety and minimizing accident-related risks.
Zitieren
APA
Sahu, D., & Soni, P. R. (2026). Road Traffic Accident Severity Prediction Using Machine Learning. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(04), 1-9. https://doi.org/10.55041/ijsrem59437
Vancouver
Sahu D, Soni PR. Road Traffic Accident Severity Prediction Using Machine Learning. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(04):1-9. doi:10.55041/ijsrem59437
BibTeX
@article{Sahu2026,
author = {Sahu, Durgeshwari and Soni, Prof. Ravikant},
title = {Road Traffic Accident Severity Prediction Using Machine Learning},
journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
year = {2026},
volume = {10},
number = {04},
pages = {1--9},
doi = {10.55041/ijsrem59437}
}
EUVIMED