Forecasting Road Traffic Accidents in Lagos State, Nigeria
1,* Naallah, A.B., 2Ibitoye, A.B., 2Subair, S.O.
1, Department of Civil Engineering, Kwara State Polytechnic, Ilorin, Kwara State, Nigeria.
2Department of Civil and Environmental Engineering, Kwara State University, Malete
DOI: 10.36108/laujoces/5202.41.0130
Abstract
Road traffic accidents (RTAs) indicate significant challenges worldwide, with developing countries like Nigeria facing severe impacts due to rapid urbanization, inadequate infrastructure, and poor traffic law enforcement. Lagos State, a densely populated metropolitan area, has recorded a consistent increase in RTAs, contributing to high economic costs and public health strain. This study examines temporal patterns in RTAs in Lagos from 2014 to 2023, employing advanced time series analysis to forecast trends for 2024–2028 with the use of Seasonal Autoregressive Integrated Moving Average (SARIMA) Model. The findingsreveal notable seasonal variations, with December consistently reporting the highest accident rates, likely influenced by festive activities. SARIMA (0,1,1)(2,0,0)[12] emerged as the best-fit model, demonstrating robust performance in capturing seasonal and trend components due to the lowest Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) values of 697.9351 and 705.8249 respectively. Predictions indicate a continued upward trend in RTAs, emphasizing the need for proactive interventions. The study offer actionable insights for urban planners, policymakers and stakeholders to prioritize safety measures, optimize resource allocation, and implement data-driven strategies for mitigating RTAs. The study underscores the utility of predictive modeling in solving the problems of urban traffic accidents in Lagos and similar contexts globally. The study provides a framework for both motorists and traffic regulatory agencies to work together towards enhancing road safety. By leveraging data and predictive modeling, stakeholders can create a safer urban environment, ultimately reducing the incidence of road traffic accidents.
.
Keywords: Accident trend, Road traffic accident, Traffic safety, Forecasting, Modeling sustainability.