A Context Integrated Relational Spatio-Temporal Model for Demand and Supply Forecasting
arXiv:2009.12469
Abstract
Traditional methods for demand forecasting only focus on modeling the temporal dependency. However, forecasting on spatio-temporal data requires modeling of complex nonlinear relational and spatial dependencies. In addition, dynamic contextual information can have a significant impact on the demand values, and therefore needs to be captured. For example, in a bike-sharing system, bike usage can be impacted by weather. Existing methods assume the contextual impact is fixed. However, we note that the contextual impact evolves over time. We propose a novel context integrated relational model, Context Integrated Graph Neural Network (CIGNN), which leverages the temporal, relational, spatial, and dynamic contextual dependencies for multi-step ahead demand forecasting. Our approach considers the demand network over various geographical locations and represents the network as a graph. We define a demand graph, where nodes represent demand time-series, and context graphs (one for each type of context), where nodes represent contextual time-series. Assuming that various contexts evolve and have a dynamic impact on the fluctuation of demand, our proposed CIGNN model employs a fusion mechanism that jointly learns from all available types of contextual information. To the best of our knowledge, this is the first approach that integrates dynamic contexts with graph neural networks for spatio-temporal demand forecasting, thereby increasing prediction accuracy. We present empirical results on two real-world datasets, demonstrating that CIGNN consistently outperforms state-of-the-art baselines, in both periodic and irregular time-series networks.
9 pages, 6 figures, submitted to AAAI
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Inductive Representation Learning on Large Graphs
- Spectral Networks and Locally Connected Networks on Graphs
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- Predicting Station-level Hourly Demands in a Large-scale Bike-sharing Network: A Graph Convolutional Neural Network Approach
- Gated Graph Sequence Neural Networks
- Measuring correlations between non-stationary series with DCCA coefficient
- Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery
- Graph-Based Deep Modeling and Real Time Forecasting of Sparse Spatio-Temporal Data