Demand Prediction of Bicycle Sharing Systems
نویسندگان
چکیده
Bike sharing system requires prediction of bike usage based on usage history to re-distribute bikes between stations. In this study, original data was collected around Washington D.C. area in 2011 and 2012. Original data is processed by several feature engineering approaches based on analysis and understanding of the data. Ridge linear regression, support vector regression (εSVR), random forest, and gradient boosted tree are applied to predict usage of bike sharing system in an hour based on the conditions of the hour. Test root-mean-squared logarithm error (RMSLE) is achieved at 0.82, 0.34, 0.31, and 0.31 respectively after model parameters optimization and feature selection. Keywords—Bike-Share System, Support Vector Regression, Radom Forest, Machine Learning.
منابع مشابه
Balancing public bicycle sharing system by defining response rates for destinations
Public Bicycle Sharing System (PBSS) is used as a way to reduce traffic and pollution in cities. Its performance is related to availability of bicycles for picking up and free docks to return them. Existence of different demand types leads to the emergence of imbalanced stations. Here, we try to balance inventory of stations via defining maximal response rates for each type of rental request. I...
متن کاملMulti-Agent System for Demand Prediction and Trip Visualization in Bike Sharing Systems
This paper proposes a multi agent system that provides visualization and prediction tools for bike sharing systems (BSS). The presented multi-agent system includes an agent that performs data collection and cleaning processes, it is also capable of creating demand forecasting models for each bicycle station. Moreover, the architecture offers API (Application Programming Interface) services and ...
متن کاملA Public Bicycle Sharing System Considering Renting and Middle Stations
Recently, public bicycle sharing system (PBSS) has become one of the most favorite urban transportation systems that can help governments to decrease environmental problems such as pollution and traffic. This paper studies a sharing system that includes two types of stations. The first category contains stations that users can rent or return back bicycles and each bicycle can be rented by any n...
متن کاملHow barriers and motivators can affect Mashhad citizens' usage of bicycle sharing system: A qualitative approach
The purpose of the present study is to identify the motivators and the barriers of using Mashhad’s Bicycle Sharing System. Bicycle sharing systems (BSS) are carried out in different ways, so each system has specific features and conditions. The authors of this paper have used a qualitative approach with a thematic analysis method for an in-depth analysis of the motivators and barriers of Mashha...
متن کاملExamining the Impact of Sample Size in the Analysis of Bicycle Sharing Systems
Given the growing installation of bicycle-sharing systems (BSS) across the world, there is a gradual increase in research on BSS over the past few years. Research efforts examining BSS employed a wide range of sample size depending on the temporal or spatial aggregation. The main objective of this paper is to investigate the impact of sample size on BSS analysis using data from New York City’s ...
متن کامل