A Match-Then-Predict Method for Daily Traffic Flow Forecasting Based on Group Method of Data Handling

Forecasting daily traffic flow in the future is one of the most critical components in traffic management to improve operational efficiency. This article aims to address the daily traffic flow forecasting problem given historical data. Because the traffic flow pattern is strongly correlated with contextual factors, we propose a match-then-predict method which integrates contextual matching and time series prediction based on group method of data handling (GMDH) algorithm. From a Seattle-based case study, we show that the contextual matching can significantly improve the prediction accuracy. We also show that the proposed method can in general outperform alternative prediction methods in daily traffic flow forecasting in terms of prediction accuracy. In addition, further analysis using data from other cities and applying the proposed method to forecast speed also support the benefits of the proposed method against alternative prediction methods.