Weight stacking decision tree-based short-time public transport passenger flow prediction method and system

Abstract

The invention discloses a short-time public transport passenger flow prediction method and system based on a weight stacking decision tree. The method comprises the following steps: 1) preprocessing bus IC card data, and aggregating the data into hour passenger flow data; 2) acquiring feature data of a to-be-detected route according to the location of the bus route and the time interval of the historical passenger flow, establishing a feature matrix and performing normalization operation; 3) carrying out independence test on the obtained features, carrying out correlation test on different features and prediction labels, and carrying out normal distribution test on the features; 4) constructing a weight stacking gradient lifting tree model; 5) training the training set through the weight stacking gradient boosting tree model, and then predicting the passenger flow in the prediction period to obtain a prediction result. The method has higher prediction precision and prediction stability, can give full play to the value of big data in the public transport field, effectively extracts the relevance between the multi-source impact factor and the passenger flow, and achieves the more accurate prediction of the short-term passenger flow of the public transport.

Description

technical field [0001] The invention relates to the research field of intelligent traffic passenger flow prediction and machine learning technology, in particular to a short-term bus passenger flow prediction method and system based on weight stacking decision trees. Background technique [0002] With the development of society and economy, the transportation demand of urban residents and the traffic load faced by the urban public transportation system are increasing day by day. Large-scale traffic congestion incidents frequently occur in major first-tier cities such as Beijing, Shanghai and Guangzhou in recent years. In order to improve the increasingly severe travel environment in the city, alleviate the pressure of urban traffic, and improve the level of passenger transport service, the improvement of urban public transport system and the forecast of bus passenger flow are becoming more and more important. At present, most of the investment in the domestic public transpor...

AI Technical Summary

Problems solved by technology

The prediction accuracy and accuracy of these methods and models are better than traditional methods, and there are relatively mature application scenarios in the fields of e-commerce and electric power. There are also a small number of scholars at home and abroad who use this new type of prediction method in the transportation field. SVM and deep learning methods have problems such as complex parameter adjustment, long training time and high dependence on data sets.

Images