Bike Sharing Demand

Predicting bike-sharing demand is crucial for optimizing the efficiency and user experience of these increasingly popular urban transportation systems. Current research focuses on developing sophisticated forecasting models, employing techniques like graph neural networks, convolutional neural networks (including irregular convolutions), and deep learning frameworks enhanced with cartogram approaches to capture complex spatiotemporal dependencies and account for factors like user demographics and interactions with other transportation modes. These advancements aim to improve bike redistribution strategies, optimize station placement, and enhance overall system management. The resulting improvements in prediction accuracy have significant implications for both urban planning and the sustainability of bike-sharing programs.

Papers

March 28, 2024

Graph-Based Optimisation of Network Expansion in a Dockless Bike Sharing System
Mark Roantree, Niamh Murphi, Dinh Viet Cuong, Vuong Minh Ngo
Spatial Temporal Graph Spatiotemporal Dynamical System Bike Sharing System Spatiotemporal Dynamic Bike Sharing Demand Efficient Optimisation Expandable Network

March 24, 2024

Improving Demand Forecasting in Open Systems with Cartogram-Enhanced Deep Learning
Sangjoon Park, Yongsung Kwon, Hyungjoon Soh, Mi Jin Lee, Seung-Woo Son
Deep Learning Framework Graph Attention Long Term Prediction Demand Forecasting Prediction Framework Map Element Learning Bike Sharing Demand

November 10, 2023

An Interpretable Machine Learning Framework to Understand Bikeshare Demand before and during the COVID-19 Pandemic in New York City
Majbah Uddin, Ho-Ling Hwang, Md Sami Hasnine
Covid 19 Pandemic Machine Learning Framework Bike Sharing System Pre Pandemic Bike Sharing Demand

December 18, 2022

Predicting Citi Bike Demand Evolution Using Dynamic Graphs
Alexander Saff, Mayur Bhandary, Siddharth Srivastava
Dynamic Graph Neural Network Model Bike Sharing System Time Varying Demand Bike Sharing Demand

November 16, 2022

Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction using Domain-Adversarial Graph Neural Networks
Yuebing Liang, Guan Huang, Zhan Zhao
Demand Prediction Relational Graph Bike Sharing System Knowledge Adaptation Bike Sharing Demand

March 18, 2022

Bike Sharing Demand Prediction based on Knowledge Sharing across Modes: A Graph-based Deep Learning Approach
Yuebing Liang, Guan Huang, Zhan Zhao
Demand Forecasting Knowledge Sharing Motor Augmented Mode Bike Sharing System Graph Based Deep Learning Bike Sharing Demand Ride Hailing Data

February 9, 2022

Improving short-term bike sharing demand forecast through an irregular convolutional neural network
Xinyu Li, Yang Xu, Xiaohu Zhang, Wenzhong Shi, Yang Yue, Qingquan Li
Convolutional Neural Network Temporal Dependency Travel Demand Bike Sharing System Bike Sharing Demand

Bike Sharing Demand

Papers

Graph-Based Optimisation of Network Expansion in a Dockless Bike Sharing System

Improving Demand Forecasting in Open Systems with Cartogram-Enhanced Deep Learning

An Interpretable Machine Learning Framework to Understand Bikeshare Demand before and during the COVID-19 Pandemic in New York City

Predicting Citi Bike Demand Evolution Using Dynamic Graphs

Cross-Mode Knowledge Adaptation for Bike Sharing Demand Prediction using Domain-Adversarial Graph Neural Networks

Bike Sharing Demand Prediction based on Knowledge Sharing across Modes: A Graph-based Deep Learning Approach

Improving short-term bike sharing demand forecast through an irregular convolutional neural network