Machine Learning-Based Traffic Flow Prediction and Management

Artificial Intelligence (AI) and data analytics are used by a machine learning-based traffic prediction and management to optimize transport networks, improve safety, and improve traffic management. By combining machine learning (ML) with real-time and historical data analysis, ITS makes predictive modeling and automated decision-making possible. This study suggests a hybrid model for traffic prediction based on Random Forest (RF) and Long Short Term Memory (LSTM). The performance is evaluated with Stand alone RF, K-Nearest Neighbors (KNN) and Naïve Bayes (NB) algorithms. The experimental results show that the RF + LSTM hybrid model has better performance than other methods with an accuracy of 95%, precision of 94%, recall of 94% and a F1-score of 93%. The top traffic predicting model is RF because it can handle structured data and LSTM can recognize sequential patterns. The study contributes to the development of more effective traffic management plans in smart cities by highlighting the use of hybrid models in predicting traffic.