A Comprehensive Analysis of Road Traffic Prediction Using Machine Learning Algorithms

Road traffic prediction provides dynamic directions and information for traffic management, improves road safety, forecasts traffic flow density, and fosters effective driving arrangements. Traffic flow forecasting is essential for urban development. Therefore, intelligent traffic management systems are increasingly being utilized by transportation planners and government agencies to plan for informed construction projects. The challenges posed by temporal and spatial dependencies in traffic flow prediction are further compounded by limitations in monitoring equipment. To address these challenges, Machine Learning (ML) and Deep learning (DL) techniques are employed in road traffic prediction, allowing for the handling of both historical and actual time information. This integration enhances the accuracy of traffic forecasts by studying both historical data and real-time trends. The ML and DL techniques deployed in road traffic prediction include Support Vector Regression (SVR), Logistic Regression (LR), Random Forest algorithm, K-Nearest Neighbor (KNN), Auto Regressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM), Convolutional Neural Network classifier (CNN), and Cross-Modality CNN (CM- CNN). This survey analyses methodologies and advancements in road traffic prediction, contributing to the development of improved traffic management systems.