Multivariate Demand Forecasting for Rental Bike Systems Based on an Unobserved Component Model
Many German cities, municipalities and transport associations are expanding their bike-sharing systems (BSS) to offer citizens a cost-effective and climate-friendly means of transport and an alternative to private motorized transport (PMT). However, operators face the challenge of generating high-qu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/24/4146 |
| _version_ | 1797460085855748096 |
|---|---|
| author | Christian Wirtgen Matthias Kowald Johannes Luderschmidt Holger Hünemohr |
| author_facet | Christian Wirtgen Matthias Kowald Johannes Luderschmidt Holger Hünemohr |
| author_sort | Christian Wirtgen |
| collection | DOAJ |
| description | Many German cities, municipalities and transport associations are expanding their bike-sharing systems (BSS) to offer citizens a cost-effective and climate-friendly means of transport and an alternative to private motorized transport (PMT). However, operators face the challenge of generating high-quality predictive analyses and time series forecasts. In particular, the prediction of demand is a key component to foster data-driven decisions. To address this problem, an Unobserved Component Model (UCM) has been developed to predict the monthly rentals of a BSS, whereby the station-based BSS VRNnextbike, including over 2000 bikes, 297 stations and 21 municipalities, is employed as an example. The model decomposes the time series into trend, seasonal, cyclical, auto-regressive and irregular components for statistical modeling. Additionally, the model includes exogenous factors such as weather, user behavior (e.g., traveled distance), school holidays and COVID-19 relevant covariates as independent effects to calculate scenario based forecasts. It can be shown that the UCM calculates reasonably accurate forecasts and outperforms classical time series models such as ARIMA(X) or SARIMA(X). Improvements were observed in model quality in terms of AIC/BIC (2.5% to 22%) and a reduction in error metrics from 15% to 45% depending on the considered model. |
| first_indexed | 2024-03-09T17:00:09Z |
| format | Article |
| id | doaj.art-f6e2a9ebb20e434a8096642610c66a6c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T17:00:09Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-f6e2a9ebb20e434a8096642610c66a6c2023-11-24T14:31:04ZengMDPI AGElectronics2079-92922022-12-011124414610.3390/electronics11244146Multivariate Demand Forecasting for Rental Bike Systems Based on an Unobserved Component ModelChristian Wirtgen0Matthias Kowald1Johannes Luderschmidt2Holger Hünemohr3Department of Design, Computer Science, Media, RheinMain University of Applied Sciences, 65197 Wiesbaden, GermanyDepartment of Architecture and Civil Engineering, RheinMain University of Applied Sciences, 65197 Wiesbaden, GermanyDepartment of Design, Computer Science, Media, RheinMain University of Applied Sciences, 65197 Wiesbaden, GermanyDepartment of Design, Computer Science, Media, RheinMain University of Applied Sciences, 65197 Wiesbaden, GermanyMany German cities, municipalities and transport associations are expanding their bike-sharing systems (BSS) to offer citizens a cost-effective and climate-friendly means of transport and an alternative to private motorized transport (PMT). However, operators face the challenge of generating high-quality predictive analyses and time series forecasts. In particular, the prediction of demand is a key component to foster data-driven decisions. To address this problem, an Unobserved Component Model (UCM) has been developed to predict the monthly rentals of a BSS, whereby the station-based BSS VRNnextbike, including over 2000 bikes, 297 stations and 21 municipalities, is employed as an example. The model decomposes the time series into trend, seasonal, cyclical, auto-regressive and irregular components for statistical modeling. Additionally, the model includes exogenous factors such as weather, user behavior (e.g., traveled distance), school holidays and COVID-19 relevant covariates as independent effects to calculate scenario based forecasts. It can be shown that the UCM calculates reasonably accurate forecasts and outperforms classical time series models such as ARIMA(X) or SARIMA(X). Improvements were observed in model quality in terms of AIC/BIC (2.5% to 22%) and a reduction in error metrics from 15% to 45% depending on the considered model.https://www.mdpi.com/2079-9292/11/24/4146smart mobilitytime series analysisunobserved component modeldemand forecastingvisualizationdashboard |
| spellingShingle | Christian Wirtgen Matthias Kowald Johannes Luderschmidt Holger Hünemohr Multivariate Demand Forecasting for Rental Bike Systems Based on an Unobserved Component Model Electronics smart mobility time series analysis unobserved component model demand forecasting visualization dashboard |
| title | Multivariate Demand Forecasting for Rental Bike Systems Based on an Unobserved Component Model |
| title_full | Multivariate Demand Forecasting for Rental Bike Systems Based on an Unobserved Component Model |
| title_fullStr | Multivariate Demand Forecasting for Rental Bike Systems Based on an Unobserved Component Model |
| title_full_unstemmed | Multivariate Demand Forecasting for Rental Bike Systems Based on an Unobserved Component Model |
| title_short | Multivariate Demand Forecasting for Rental Bike Systems Based on an Unobserved Component Model |
| title_sort | multivariate demand forecasting for rental bike systems based on an unobserved component model |
| topic | smart mobility time series analysis unobserved component model demand forecasting visualization dashboard |
| url | https://www.mdpi.com/2079-9292/11/24/4146 |
| work_keys_str_mv | AT christianwirtgen multivariatedemandforecastingforrentalbikesystemsbasedonanunobservedcomponentmodel AT matthiaskowald multivariatedemandforecastingforrentalbikesystemsbasedonanunobservedcomponentmodel AT johannesluderschmidt multivariatedemandforecastingforrentalbikesystemsbasedonanunobservedcomponentmodel AT holgerhunemohr multivariatedemandforecastingforrentalbikesystemsbasedonanunobservedcomponentmodel |