• 2025-04-25
• W.O. Adedeji, S. Oyelami, A.T. Oyewo, A.G Abioye, B.J. Ojerinde, A.O. Adekoya
• Volume 1, Issue 1

Abstract

This study proposes a machine learning-based traffic prediction system using Long Short-Term Memory (LSTM) networks to forecast urban traffic conditions. The model integrates real-time traffic sensor data, GPS traces, and environmental factors (e.g., weather) to predict congestion patterns with high accuracy. Evaluated against accuracy, precision, recall, and F1-score, the LSTM-based approach outperforms traditional methods like linear regression and decision trees. The results demonstrate the effectiveness of deep learning in traffic forecasting and reveal critical factors influencing congestion. This work underscores the potential of AI-driven solutions for improving traffic management systems in smart cities. Future research will focus on real-time deployment and model optimization for scalable urban applications.