Passenger Flow Prediction Using Smart Card Data from Connected Bus System Based on Interpretable XGBoost

Abstract

Bus passenger flow prediction is a critical component of advanced transportation information system for public traffic management, control, and dispatch. With the development of artificial intelligence, many previous studies attempted to apply machine learning models to extract comprehensive correlations from transit networks to improve passenger flow prediction accuracy, given that the variety and volume of traffic data have been easily obtained. The passenger flow on a station is highly affected by various factors such as the previous time step, peak hours or nonpeak hours, and extracting the key features from the data is essential for a passenger flow prediction model. Although the neural networks, k -nearest neighbor, and some deep learning models have been adopted to mine the temporal correlations of the passenger flow data, the lack of interpretability of the influenced variables is still a big problem. Classical tree-based models can mine the correlations between variables and rank the importance of each variable. In this study, we presented a method to extract passenger flow of different routes on the station and implemented a XGBoost model to find the contributions of variables to the prediction of passenger flow. Comparing to benchmark models, the proposed model can reach state-of-the-art prediction accuracy and computational efficiency on the real-world dataset. Moreover, the XGBoost model can interpret the predicted results. It can be seen that period is the most important variable for the passenger flow prediction, and so the management of buses during peak hours should be improved.

Operationalizing Digitainability: Encouraging mindfulness to harness the power of digitalization for sustainable development

“…In our analysis, a synergic impact is observed in relation to SDG 9.1.1 (rural population near an all-season road) and SDG 9.1.2 (transport) since AI for land management might support the mapping and monitoring of population close to road facilities [51,188,189] as well as the volume of passengers and freight from Big Data coming from transportation systems [190][191][192], and their evolution patterns over time. An ambivalent impact regarding the contribution to SDG 9.4.1 (CO2 emissions) is observed since AI for land could be useful to calculate the carbon footprint based on LCAs from different activities, forest extension, and soil features acting as carbon sinks [193,194].…”

Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data

“…Before operators could automatically collect large quantities of occupancy data, surveyors were tasked with counting passengers at critical locations of the transportation network to assess the passenger numbers and derive the transportation demand [7]. With the emergence of ITS around 2000, data collection has been simplified [17]: Data sources such as the data of automated fare collection (AFC) systems [18], or APC systems with cameras, light barriers, LiDAR [19], weight sensors [20], Wi-Fi data [21,22], or crowdsourcing [23,24] became available. Some of these data sources continually transmit their data to an ITS; thus, real-time passenger information systems became possible.…”

“…Ensemble Learning combines many smaller machine learning models with low accuracy into a larger model with better accuracy. Random forest (RF) [43], gradient boosting regression tree [43], LightGBM [44], and XGBoost [18] algorithms have been proposed for passenger load and flow prediction. Boosted models often have an advantage over non-boosted models, but for noisy data, they tend to overfit.…”

XGBoost-Based E-Commerce Customer Loss Prediction

“…Data imbalance is an obvious problem for customer loss forecasting model. The experimental purpose of this section is to explore the influence of different sampling methods on customer loss prediction model [ 26 , 27 ]. In this experiment, there are four methods to deal with data imbalance: (1) imbalance; (2) Random upsampling; (3) SMOTE; and (4) SMOTE Tomek-link.…”