Zone prioritisation for transit improvement using potential demand estimated from smartcard data
Document Type
Journal Article
Publication Date
2023
Subject Area
technology - ticketing systems, ridership - demand, ridership - modelling, planning - service improvement, planning - methods
Keywords
Smartcard data, transit improvement, gradient boost, potential demand, public transit demand
Abstract
It is of utmost importance to understand the networkwide transit service needs for future planning and effective funding allocations. For this purpose, this study proposes a methodology that uses a zone’s transit potential demand as an indicator to prioritise them for public transport-related improvements. This study utilises observed demand (referred to as served demand) from smartcard data to estimate the potential demand. The smartcard data is used to estimate the observed demand of a zone, based upon which high and low trip zones are segregated. An ensemble tree-based Gradient Boosting model is trained and validated using observed trips by employing demographics, socio-economic, and geographic variables. From the analysis, zones with high and low potential demand are identified. Based on the estimated potential demand per unit area, all the zones are clustered into four groups identifying the areas with the lowest, low, medium, and high transit improvement requirements.
Rights
Permission to publish the abstract has been given by Taylor&Francis, copyright remains with them.
Recommended Citation
Hussain, E., Bhaskar, A., & Chung, E. (2023). Zone prioritisation for transit improvement using potential demand estimated from smartcard data. Transportmetrica A: Transport Science, 19(2), 2028930.
