Modeling of Vehicle Transportation Optimal Route Recommendation System Based on Decision Tree Classification Algorithm

Before traveling, travelers are interested in how to find an optimal path from the starting point to the end point. Decision tree is one of the most widely used models in classification applications. The existing theoretical research on vehicle transportation route selection is relatively absent, mostly about the transportation route selection of articles and hazardous wastes. The transportation risks in these studies only consider the objective risks such as the probability of accidents or the density of people affected by the passing area. Although it is enlightening to the vehicle route selection, it is not fully applicable. Continuous discretization of attributes and dimension reduction of high-dimensional and large-scale data are also key technologies to expand the application range of decision tree algorithm. From the point of view of vehicle transportation considering the time factor, the government stipulates that all provinces have strict traffic restriction system, as well as the changes of traffic flow, the number of people near road sections and customers’ satisfaction with the delivery time. This series of realistic reasons reflects the importance of time factor to the route optimization of transport vehicles. Decision tree can analyze the patterns and rules useful to users in the learning data from a large amount of data, and use these learned patterns and rules. The decision tree does not need to spend a lot of time and thousands of iterations to train the model. It is suitable for large-scale data sets. In addition to the information in the training data, it does not need other additional information, and shows good classification accuracy. Therefore, aiming at the problem of route selection of transportation vehicles while driving, this paper uses the decision tree classification algorithm to construct a linear layout model of the optimal route of vehicle transportation.