BANDUNG CITY TRAFFIC CLASSIFICATION MAP WITH MACHINE LEARNING AND ORDINARY KRIGING

Congestion is a problem that occurs when the number of vehicles exceeds capacity road and vehicle speed slows down. This issue one main issues in big cities, including Bandung. In this study, study aims to reduce traffic congestion city The classification process uses Support Vector Machine (SVM), Naive Bayes, Ordinary Kriging methods. data used counting from ATCS Bandung direct observation. count obtained contains 3804 rows. Three experimental scenarios were carried out validate effectiveness model used, performance first without oversampling, second with third hyperparameter adjustment. results show method has higher accuracy than Bayes method, which 93%, while an 90%. application tuning over-sampling proven overcome imbalance get better results. addition, best are making maps, namely assisted ordinary kriging predict surrounding area. map southern area more unstable other areas