Passenger demand forecasting in scheduled transportation

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The aim of this review article is to provide a synoptic and critical evaluation of the extensive research that has been performed in demand forecasting in the scheduled passenger transportation industry, specifically in the last few decades. The review begins with an attempt to classify and tabulate the research according to the properties of proposed models, their objectives and application areas in industry in different stages of the planning cycle. This is followed by an assessment of forecast methodologies with suggestions on different methodologies that industry practitioners can adopt to suit their specific needs and recommendations towards future directions of research. We also provide a look into the cross cutting concerns that need to be addressed by all forecasting systems irrespective of the domain or planning stage, such as demand unconstraining, aggregation and the role of expert judgement to incorporate the effect of other extraneous factors that might affect the demand. We conclude from our study that there is a lack of standardization in the way in which methods are described and tested. As a result, there is a lack of cumulative knowledge building. To redress this concern, we propose open source testbeds to facilitate benchmarking of new models. We also propose a checklist as a guideline to standardize the research reports and suggest that when proposing newer models, researchers may consider including a comparative study with existing standard models in research report.
Original languageEnglish
Pages (from-to)797-810
Number of pages14
JournalEuropean Journal of Operational Research
Volume286
Issue number3
Early online date30 Oct 2019
DOIs
Publication statusPublished - 1 Nov 2020

Keywords

  • demand forecasting
  • transportation
  • seat inventory management
  • strategic planning
  • budget planning

Fingerprint Dive into the research topics of 'Passenger demand forecasting in scheduled transportation'. Together they form a unique fingerprint.

Cite this