Sustainability · 2016 · 177 citations · 35 references
ComputingData ScienceTransportation PlanningData MiningMachine LearningTransportationDecision TreesEnsemble MethodsPublic Transit AnalyticsTraffic Demand ForecastingTransportation AnalyticsTransportation ModelsAccuracyGradient Boosting TreesIndependent VariablesMachine Learning-based ForecastingModel Performance EvaluationPredictive Model PerformanceRegularizationSmart Card Data Analysis
Short‑term subway ridership depends on multiple factors, yet studies rarely consider bus transfer activities and temporal features. The study applies gradient boosting decision trees to predict short‑term subway ridership and capture associations with independent variables. Using smart‑card data from three Beijing subway stations and adjacent bus stops, the authors built multiple GBDT models with varying learning rates and tree complexities to optimize performance. The optimized GBDT model accurately captures nonlinear relationships, handles multicollinearity, and ranks bus transfer and temporal features, outperforming other machine‑learning methods and improving prediction in a multimodal system.
Understanding the relationship between short-term subway ridership and its influential factors is crucial to improving the accuracy of short-term subway ridership prediction. Although there has been a growing body of studies on short-term ridership prediction approaches, limited effort is made to investigate the short-term subway ridership prediction considering bus transfer activities and temporal features. To fill this gap, a relatively recent data mining approach called gradient boosting decision trees (GBDT) is applied to short-term subway ridership prediction and used to capture the associations with the independent variables. Taking three subway stations in Beijing as the cases, the short-term subway ridership and alighting passengers from its adjacent bus stops are obtained based on transit smart card data. To optimize the model performance with different combinations of regularization parameters, a series of GBDT models are built with various learning rates and tree complexities by fitting a maximum of trees. The optimal model performance confirms that the gradient boosting approach can incorporate different types of predictors, fit complex nonlinear relationships, and automatically handle the multicollinearity effect with high accuracy. In contrast to other machine learning methods—or “black-box” procedures—the GBDT model can identify and rank the relative influences of bus transfer activities and temporal features on short-term subway ridership. These findings suggest that the GBDT model has considerable advantages in improving short-term subway ridership prediction in a multimodal public transportation system.
35
Greedy function approximation: A gradient boosting machine.
Jerome H. Friedman · The Annals of Statistics · 2001 · 29K citations · Full text
Classification and Regression Trees.
John Van Ryzin, Leo Breiman, Jerome H. Friedman et al. · Journal of the American Statistical Association · 1986 · 21K citations
Jerome H. Friedman · Computational Statistics & Data Analysis · 2002 · 7.1K citations
A working guide to boosted regression trees
Jane Elith, John R. Leathwick, Trevor Hastie · Journal of Animal Ecology · 2008 · 6.5K citations · Full text
Computing, Biostatistics, Ecology +14