Simplifications for single-route transit-ridership forecasting models

Horowitz, Alan J.

doi:10.1007/bf00146945

Cited by 13 publications

(7 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ridership estimation models are frequently studied in public transit and have been reviewed multiple times (see, for example, Kain and Liu, 1999;Abdel-Aty, 2001;Wang and Skinner, 1984;Horowitz, 1984;Taylor et al, 2004;Ben-Akiva and Morikawa, 2002). Not surprisingly, these studies are framed for transit agency related questions and purposes.…”

Section: Existing Research On Transit Ridership Modeling and Decisionmentioning

confidence: 98%

Land use and transit ridership connections: Implications for state-level planning agencies

Chakraborty

Mishra

2013

Land Use Policy

View full text Add to dashboard Cite

Section: Existing Research On Transit Ridership Modeling and Decisionmentioning

confidence: 98%

Land use and transit ridership connections: Implications for state-level planning agencies

Chakraborty

Mishra

2013

Land Use Policy

View full text Add to dashboard Cite

“…Assuming that x is a set of predictor variables and f (x) is an approximation function of the response variable y, using the training data {y i , x i } γ jm I(x ∈ R jm ), where I = 1 i f x ∈ R jm ; I = 0, otherwise (1) where each tree partitions the input space into J disjoint regions R 1m , . .…”

Section: Gradient Boosting Decision Trees Approachmentioning

confidence: 99%

“…With the predicted passenger demand information, commuters can better arrange their trips by adjusting departure times or changing travel modes to reduce delay caused by crowdedness; subway operators can proactively optimize appropriate timetables, allocate necessary rolling stock and disseminate early warning information to passengers for extreme event (e.g., stampede) prevention. Existing studies mainly lie in long-term transit ridership prediction for public transport planning as the part of traditional four-step travel demand forecasting [1]. The typical approach is to construct linear ridership generated by feeder buses, are incorporated into the GBDT model for short-time subway ridership.…”

Section: Introductionmentioning

confidence: 99%

Predicting Short-Term Subway Ridership and Prioritizing Its Influential Factors Using Gradient Boosting Decision Trees

et al. 2016

View full text Add to dashboard Cite

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.

show abstract

“…While simplified versions of the traditional four-step process (Horowitz 1984;Horowitz and Metzger 1985) have been developed for specifically accessing these impacts, most previous work has focused on direct demand models at the route-level (Alperovich et al 1977;Cherwony and Polin 1977;Kemp 1981;Menhard and Ruprecht 1983;Stopher and Mulhall 1992;Hartgen and Horner 1997). While these route-level models avoid some of the problems with the traditional four-step process, they have their own difficulties (Alperovich et al 1977).…”

Section: Literature Reviewmentioning

confidence: 99%

Transit Ridership Models at the Stop Level

Cutr¹

2004

View full text Add to dashboard Cite

This report documents the development of a ridership model at the stop level for Transit Level of Service (TLOS), a software package of the Florida Department of Transportation (FDOT) for measuring transit availability and mobility. This report is in two separate parts. This first part discusses issues in formulating a ridership model on several aspects, including literature review, the study area, analytical framework, data needs, and model-formulation issues. For each issue, the discussion focuses on the alternative approaches to dealing with the issue, any resolution, and CUTR's recommendation, if different from the resolution. The second part discusses the data made available by Kittelson and Associates, Inc. under a separate contract with the FDOT, the data used for model estimation, and the selection of a final model. The final model relates average weekday boarding at a TLOS stop with six categories of factors: 1) socio-demographics in a catchment area; 2) TLOS value; 3) the street environment for pedestrians; 4) accessibility to population and employment; 5) interaction with other modes; and 6) competition with other TLOS stops. Despite some data limitations, the model fits the data well and behaves as expected.

show abstract

Simplifications for single-route transit-ridership forecasting models

Cited by 13 publications

References 3 publications

Land use and transit ridership connections: Implications for state-level planning agencies

Land use and transit ridership connections: Implications for state-level planning agencies

Predicting Short-Term Subway Ridership and Prioritizing Its Influential Factors Using Gradient Boosting Decision Trees

Transit Ridership Models at the Stop Level

Contact Info

Product

Resources

About