Using Slightly Imbalanced Binary Classification to Predict the Efficiency of Winter Road Maintenance

The prediction of efficiency scores for winter road maintenance (WRM) is a challenging and serious issue in countries with cold climates. While effective efficient WRM key contributor to maximizing transportation safety minimizing costs environmental impacts, it has not yet been included intelligent methods. Therefore, this study aims design classification model that combines data envelopment analysis machine learning techniques improve decision support systems decision-making units. proposed methodology consists six stages starts selection. Real are obtained by observing conditions equal time intervals via weather information systems, optical sensors, road-mounted sensors. Then, preprocessing performed, calculated the method classify units into inefficient classes. Next, classes considered targets algorithms, dataset split training test datasets. A slightly imbalanced binary case encountered since distributions unequal, low ratio between includes comparison different techniques. graphical numerical results indicate combination vector genetic algorithm yields best generalization performance. include analyzing variables affect using drive future insights process decision-making.