Prediction of Bike-Sharing Trip Counts: Comparing Parametric Spatial Modeling Techniques to a Geographically Weighted Xgboost Algorithm

52 Pages Posted: 1 Feb 2022

See all articles by Katja Schimohr

Katja Schimohr

affiliation not provided to SSRN

Philipp Doebler

affiliation not provided to SSRN

Joachim Scheiner

affiliation not provided to SSRN

Abstract

Transportation data is regularly analyzed using regression models. This research aims at broadening the range of methods used in this field by modeling the spatial distribution of bike-sharing trips in Cologne, Germany, applying both parametric models and a machine learning approach. Independent variables included in the models consist of land use types, elements of the transport system and sociodemographic characteristics. Out of several regression models with different underlying distributions, a Tweedie generalized additive model is chosen by its values for AIC, RMSE and sMAPE to be compared to an XGBoost model. To deal with the issue of spatial autocorrelation, spatial splines are included in the Tweedie model, while the estimations of the XGBoost model are modified using a geographically weighted regression. Both methods entail certain advantages: while XGBoost leads to far better values regarding RMSE and sMAPE and therefore to a better model fit, the Tweedie model allows an easier interpretation of the influence of the independent variables.

Keywords: bike-sharing, XGBoost, geographically weighted regression, generalized additive models

Suggested Citation

Schimohr, Katja and Doebler, Philipp and Scheiner, Joachim, Prediction of Bike-Sharing Trip Counts: Comparing Parametric Spatial Modeling Techniques to a Geographically Weighted Xgboost Algorithm. Available at SSRN: https://ssrn.com/abstract=4023131 or http://dx.doi.org/10.2139/ssrn.4023131

Katja Schimohr (Contact Author)

affiliation not provided to SSRN ( email )

No Address Available

Philipp Doebler

affiliation not provided to SSRN ( email )

No Address Available

Joachim Scheiner

affiliation not provided to SSRN ( email )

No Address Available

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
44
Abstract Views
112
PlumX Metrics