ROAD ACCIDENT SEVERITY PREDICTION USING DATA SCIENCE

Road accidents represent a major public safety concern worldwide, causing significant loss of life, injuries, and economic damage every year. Predicting the severity of road accidents before or immediately after they occur can help authorities implement preventive measures, improve emergency response, and enhance overall traffic management. The proposed system, Road Accident Severity Prediction Using Data Science, focuses on analyzing historical accident data and identifying patterns that influence accident severity. The system utilizes advanced data science and machine learning techniques to process multiple influencing factors such as weather conditions, road type, temperature, visibility, lighting conditions, and speed limits. Data preprocessing techniques including data cleaning, normalization, and categorical encoding are applied to prepare the dataset for effective modeling. Since accident datasets are often highly imbalanced, the Synthetic Minority Oversampling Technique (SMOTE) is implemented to balance the dataset and improve prediction performance. Machine learning algorithms such as Random Forest, Decision Tree, and Logistic Regression are employed to build predictive models that classify accidents into different severity levels such as minor, serious, or fatal. Feature importance analysis helps identify the most influential factors contributing to severe accidents. The model is evaluated using performance metrics such as accuracy, precision, recall, and F1-score to ensure reliable predictions. The proposed system assists traffic management authorities, policymakers, and emergency services in understanding accident patterns and implementing preventive strategies. By integrating predictive analytics with traffic safety systems, the proposed framework contributes toward reducing accident-related fatalities and improving road safety planning. Overall, this data-driven approach demonstrates how intelligent predictive systems can support smarter transportation infrastructure and enhance public safety.