Paper Key : IRJ************845
Author: Krushna Borude ,Sudhir Adhe ,Dr. Mahendra Kondekar
Date Published: 18 Apr 2025
Abstract
Road traffic accidents are a leading cause of death and injury worldwide, posing serious challenges to public safety and urban planning. This research presents a data-driven approach to analyzing vehicle accident trends using Python, Django, and Bootstrap. A real-world dataset sourced from Kaggle is utilized to examine critical factors contributing to accidents, including vehicle speed, road types, weather conditions, and vehicle categories. The primary objective is to identify recurring patterns, high-risk zones, and underlying correlations that lead to accidents. Data preprocessing techniques such as missing value treatment, outlier detection, and normalization are applied to ensure data quality. Exploratory Data Analysis (EDA) and data visualization tools such as Seaborn and Matplotlib are employed to uncover meaningful insights. A user-friendly web interface is developed using Django and Bootstrap, enabling interactive visualization and analysis for stakeholders. Findings from the study reveal significant associations between weather conditions, road surface types, and accident severity. Vehicle speed and type are also identified as major contributors to collision outcomes. The developed dashboard offers a practical tool for policymakers, traffic management authorities, and researchers to support decision-making and preventive strategies. This research demonstrates the potential of data science and web-based analytics in enhancing road safety. The system is scalable and adaptable to regional or national datasets, making it a valuable framework for real-time accident monitoring and strategic planning. The outcomes contribute to data-informed policymaking aimed at reducing accident-related injuries and fatalities.