Thesis
Bus Ridership Prediction: A Machine Learning Approach
Washington State University
Master of Science (MS), Washington State University
01/2021
DOI:
https://doi.org/10.7273/000003119
Handle:
https://hdl.handle.net/2376/121688
Abstract
Bus ridership is a key component of transit systems nationwide and increasing the share of bus ridership is an important part of reducing externalities like congestion, pollution, and traffic accidents. However, bus ridership has been on the decline in recent years as personal automobiles remain the most popular mode of transport. In order to equip transit authorities with the information they need to make routing, location, and service decisions to induce demand, a predictive ridership demand model is developed. This model will serve as the foundation for a transit planning decision support tool. With the advent of automated passenger count (APC) systems and growing data availability in the transportation sector, machine learning methods are increasingly viable for prediction problems. This paper explores how best to develop a machine learning model for predicting bus ridership within a rural transit network.
Metrics
26 File views/ downloads
54 Record Views
Details
- Title
- Bus Ridership Prediction: A Machine Learning Approach
- Creators
- Brandon Bullard
- Contributors
- Mark Gibson (Advisor)Jake Wagner (Committee Member)Alan Love (Committee Member)
- Awarding Institution
- Washington State University
- Academic Unit
- Agricultural, Human, and Natural Resource Sciences, College of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University
- Number of pages
- 52
- Identifiers
- 99900651898901842
- Language
- English
- Resource Type
- Thesis