Download PDFOpen PDF in browser

Estimating Passenger Demand Using Machine Learning Models: a Systematic Review

EasyChair Preprint 10716

12 pagesDate: August 15, 2023

Abstract

Machine learning approaches are increasingly used to solve varying problems in the world. This review investigated machine learning models used to estimate passenger demand. These models have the potential to provide valuable insights into passenger trip behaviour and other inferences. The estimate of passenger demand using machine learning model research and the methodologies used are fragmented. To synchronise these studies, this paper conducts a systematic review of machine learning models to estimate passenger demand. The review investigates how passenger demand is estimated using machine learning models. A comprehensive search strategy is carried out across the three main online publishing databases to locate unique 911 records. Relevant record titles, abstracts, and publication information are extracted, leaving 102 articles. In addition, the articles are evaluated according to the eligibility requirements. This procedure yields 21 full-text papers for data extraction. Three research thematic questions covering passenger data collection techniques, passenger demand interventions, and intervention performance are reviewed in detail. The results of this study suggest that mobility records, LSTM-based models, and performance metrics play a critical role in performing passenger demand prediction studies. Model evaluation was mostly restricted to 3 performance metrics. Furthermore, the review determined an overreliance on the long- and short-term memory model to estimate passenger demand. Therefore, minimising the limitation of the LSTM model will generally improve the estimation models. Additionally, having an acceptable train set to avoid overfitting is crucial. Furthermore, it is advisable to consider multiple metrics to have a more comprehensive evaluation.

Keyphrases: Transportation, machine learning, passenger demand, public transport

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:10716,
  author    = {Adjei Boateng and Charlse Anum Adams and Emmanuel Kofi Akowuah and Augustus Ababio-Donkor},
  title     = {Estimating Passenger Demand Using Machine Learning Models: a Systematic Review},
  howpublished = {EasyChair Preprint 10716},
  year      = {EasyChair, 2023}}
Download PDFOpen PDF in browser