Short‐term railway passenger demand forecast using improved Wasserstein generative adversarial nets and web search terms

Abstract

Accurately predicting railway passenger demand is conducive for managers to quickly adjust strategies. It is time-consuming and expensive to collect large-scale traffic data. With the digitization of railway tickets, a large amount of user data has been accumulated. We propose a method to predict railway passenger demand using web search terms data. In order to improve the prediction accuracy, we improved Wasserstein Generative Adversarial Nets (WGAN), which were good at generating and identifying data, by adding a predictor and supervised learning adversarial training to predict railway passenger demand. The improved WGAN could generate virtual data to expand real data, and use parallel data to predict railway passenger demand. We used search times of web search terms on different devices as training data to predict railway passenger demand in Beijing. The results show that the change in demand for railway passenger lags behind the change in the data of web search terms by one month. It is suitable for forecasting in advance. Compared with other forecasting methods, the improved WGAN performance is better, and the mean absolute percentage error is 1.98%. Because it can use mixed data for training and prediction, it has stronger adaptability when data scale decreases. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Next Place Prediction Model: A Literature Review

“…The purposes of the studies can be divided between individual mobility prediction, which captures regularities, and tendencies of individual's mobility behaviours using mobility data, and population mobility prediction, which captures mobility behaviours at a population/group of individual level, capturing aggregated trends. The first predictions are carried out mainly by means of statistic or machine learning techniques according to the data availability [8][9][10][11][12][13][20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36], while the latter can also exploit data mining techniques or agent-based modelling [6,11,24,[37][38][39][40][41][42][43][44][45][46]. The identified purposes can be further segmented from a spatial perspective by varying the unit of analysis, resulting in three prediction outcomes per purpose, i.e., trajectory recognition, next location prediction, and next trip prediction.…”

“…Finally, Multi-media includes contextual information from social media platforms, web search engines, and online check-in systems [11,12,40,44]. These methods allow to collect spatiotemporal data and provide behavioural information on the users [36]. Check-in data could provide real user trajectory in which spatiotemporal influencing factors like the travel distance and time interval between successive check-ins need to be considered [30].…”

“…For the former, mainly telephone data are used, for the latter, social media ones. With the support of these models, the public decision-maker may be able to plan measures to improve territorial planning [18,29,36,42].…”