Abstract Short-term demand prediction is important for managing transportation infrastructure, particularly in times of disruption, or around new developments. Many bike-sharing schemes face the challenges of managing service provision and bike fleet rebalancing due to the “tidal flows” of travel and use. For them, it is crucial to have precise predictions of travel demand at a fine spatiotemporal granularities. Despite recent advances in machine learning approaches (e.g. deep neural networks) and in short-term traffic demand predictions, relatively few studies have examined this issue using a feature engineering approach to inform model selection. This research extracts novel time-lagged variables describing graph structures and flow interactions from real-world bike usage datasets, including graph node Out-strength, In-strength, Out-degree, In-degree and PageRank. These are used as inputs to different machine learning algorithms to predict short-term bike demand. The results of the experiments indicate the graph-based attributes to be more important in demand prediction than more commonly used meteorological information. The results from the different machine learning approaches (XGBoost, MLP, LSTM) improve when time-lagged graph information is included. Deep neural networks were found to be better able to handle the sequences of the time-lagged graph variables than other approaches, resulting in more accurate forecasting. Thus incorporating graph-based features can improve understanding and modelling of demand patterns in urban areas, supporting bike-sharing schemes and promoting sustainable transport. The proposed approach can be extended into many existing models using spatial data and can be readily transferred to other applications for predicting dynamics in mass transit systems. A number of limitations and areas of further work are discussed.

中文翻译：

---

使用有关流量的图形结构信息来增强自行车共享系统中的短期需求预测

摘要 短期需求预测对于管理交通基础设施很重要，特别是在中断时期或新发展时期。由于旅行和使用的“潮汐流”，许多自行车共享计划面临着管理服务提供和自行车车队重新平衡的挑战。对他们来说，以精细的时空粒度准确预测出行需求至关重要。尽管最近在机器学习方法（例如深度神经网络）和短期交通需求预测方面取得了进展，但使用特征工程方法来为模型选择提供信息的研究相对较少。本研究从现实世界的自行车使用数据集中提取描述图结构和流动交互的新时滞变量，包括图节点 Out-strength、In-strength、Out-degree、度数和 PageRank。这些被用作不同机器学习算法的输入，以预测短期自行车需求。实验结果表明基于图形的属性在需求预测中比更常用的气象信息更重要。当包含时滞图信息时，不同机器学习方法（XGBoost、MLP、LSTM）的结果会有所改善。发现深度神经网络比其他方法能够更好地处理时滞图变量的序列，从而实现更准确的预测。因此，结合基于图形的特征​​可以提高对城市地区需求模式的理解和建模，支持自行车共享计划并促进可持续交通。所提出的方法可以使用空间数据扩展到许多现有模型中，并且可以很容易地转移到其他应用程序中以预测公共交通系统中的动态。讨论了一些限制和进一步工作的领域。