Identification of Fee Evasion Behavior in Expressway Changing Path Based on Random Forest
In order to improve the efficiency of identifying toll evasion behavior by changing paths on highways,toll evasion behavior was studied by changing paths.A model for identifying toll evasion behavior by changing paths on highways based on random forests was established,which can effectively identify such behavior of toll evasion and assist relevant management departments of highways in recovering evaded fees.Firstly,the original toll data were analyzed to filter out the fields related to this study,and the 12 initial features that can be inputted into the model were obtained after arithmetic.Secondly,the features with covariance were eliminated by calculating the variance inflation factor(VIF)and tolerance(TOL)values of each feature,and the Boruta algorithm was used to filter out the high-importance features("whether the driving direction is consistent""whether the entry and exit stations are consistent""travel time"and"minimum fare mileage").Thirdly,the data set was balanced using the SMOTETomek integrated sampling technique.Then,the grid search method was used to tune the hyperparameters of the random forest.Finally,the model built was utilized for training and recognition,and the recognition effect was compared with that of the benchmark model.The results show that the model developed can better recognize the toll evasion behavior by changing paths on highways,and the Macro-F1 score reaches 0.966,which is better than the extreme gradient boost(XGBoost)(0.943 1),decision tree(DT)(0.956 3)and gradient boosting decision trees(GBDT)(0.938 2),and it can provide reference for operation management departments to inspect such toll evasion vehicles.
random forest(RF)toll evasion by changing pathBoruta algorithmdata imbalance processing
万方数据
维普
