A review of bike volume prediction studies

Abstract

No previous research provided a comprehensive review of the bicycle volume estimation techniques assessing the current research gaps in data and modeling makes it challenging to understand the most effective and accurate strategies to estimate bicycle volumes. This article provides a detailed review of 58 studies published from 1996 to 2021. The review results indicate that conventional modeling approaches such as Linear regression, Negative Binomial, Poisson regressions, and a factor-up method represent the most popular econometric statistical models for bicycle volume estimation, while a decision tree is popular among machine-learning-based techniques due to its simplicity and ease of application, interpretation, and estimation with small data sets. In addition, Strava data, Socio-demographic variables, and bicycle facilities significantly contribute to the predictions. The study documents the current research gaps and recommends future research directions to improve data source evaluations, variable creations, modeling, and scalability/transferability advancements.