Road Accident Severity Prediction Using Machine Learning Project

The majority of fatalities and serious injuries occur as a result of incidents involving motor vehicles. If the traffic  management system is going to do its job of reducing the frequency and severity of traffic accidents, it needs a model for doing so. In this paper, we combine the results of three machine learning algorithmslogistic regression, decision tree, and random forest classifierto build a predictive model. In order to forecast the severity of accidents in different regions, we used ML algorithms on a dataset of accidents from the United States. In addition, we examine vast quantities of traffic data, extracting  helpful accident patterns in order to pinpoint the factors that have a direct bearing on road accidents and make actionable suggestions for improvement. When compared to two other ML algorithms, random forest performed best on accuracy. The severity rating in this paper is not meant to reflect the severity of injuries sustained, but rather how the accident affects traffic flow. Accident severity, decision trees, random forests, and logistic regression are all terms that are often used to describe this area of study
Road accidents have become a major concern globally, causing a significant number of fatalities and injuries every year. The aim of this project is to predict road accidents severity using machine learning
techniques, in order to reduce their occurrence and mitigate the associated risks. The project uses data collected from various sources such as accident reports, weather conditions, and road infrastructure to train and evaluate various supervised learning algorithms and predict the accident severity. Four algorithms were compared, including Decision Tree, Naive Bayes, Random forest . Most probably occurring road accident locations are identified and that particular region is indicated as black pot. The proposed method can be used to provide real-time risk information to road users, helping them to make informed decisions and avoid potential accidents. The project highlights the importance of using machine learning techniques in road safety analysis, providing a foundation for further research in this field.

About Dataset

Dataset Link - https://www.kaggle.com/datasets/s3programmer/road-accident-severity-in-india

The data set has been prepared from manual records of road traffic accidents for the years 2017–22. All the sensitive information has been excluded during data encoding, and finally, it has 32 features and 12316 instances of the accident. Then it is preprocessed for the identification of major causes of the accident by analyzing it using different machine learning classification algorithms. Road.csv is the preprocessed dataset.

Running the web app

Locally

  • Install requirements
    pip install -r requirements.txt --user
  • Run flask web app
    python app.py

Download Link