NORMA eResearch @NCI Library

Demand prediction in a bike-sharing system using machine learning techniques

Rawat, Ashish (2020) Demand prediction in a bike-sharing system using machine learning techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


A bike-sharing system provides people with a sustainable mode of transportation and has beneficial effects for both the environment and the user. And the city-wide accessibility and low cost has exponentially increased its popularity. Nonetheless, the increased usage has led to create issues like unavailability of bikes and docks at bike stations. Therefore, the study aims to predict the demands of a bike sharing system using machine learning models. And also analyses comprehensive effect of the time dependent and inter-station relationship on predicting the demands. The Metro bike-share data of 2019 consisting of more than 2 million records of bikes trip was used in the research. The original data files lacked the demand attributes, required for the research and demanded extensive data processing and transformation. Four machine learning models were employed for predicting the demands; ARIMA, LSTM, STGCN and TAGCN. And parameters such as RMSE, MSE and MAE were used for evaluating the models. The performance of the models was found to be vary with the time interval used in transforming the data. And the best performance was achieved by the STGCN with comparatively small RMSE values of 0.76 and 0.37 for bikes and docks demand respectively. The approach successfully addressed the shortcomings highlighted in Kim et al. (2019) in resolving the inclusion of new bike station in the system and performed well.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 20 Jan 2021 18:20
Last Modified: 20 Jan 2021 18:20

Actions (login required)

View Item View Item