Travel time reliability prediction by genetic algorithm and machine learning models

Abstract

Travel time reliability is known to be a critical issue in the contexts of both travellers' choices and decisions and freight transportation. The temporal variability of travel time is known as reliability and is affected by numerous factors. Traffic volume, incidents and inclement weather are among the most profound factors, and their effects have been the subject of many studies. The work reported in this article is unique due to the simultaneous implementation of a genetic algorithm (GA) with multiple machine learning (ML) methods. A GA can eliminate overfitting, which is a common problem in ML models. The numerical results showed that the performance of the K-nearest neighbours method was significantly enhanced when a GA was imposed on it. In terms of the stability ratio, a 12% decrease was observed; the mean squared errors for the training set and the testing set decreased, but the reductions were not significant. To further illustrate the advantages of GA implementation, the numbers of predictions with a mean absolute percentage error greater than 0.05 were compared and a notable reduction was found. Sensitivity analysis was carried out to determine how the planning time index responds to fluctuations of independent variables.