GEANN: Scalable Graph Augmentations for Multi-Horizon Time Series Forecasting
This addresses forecasting for time series with insufficient historical data, such as new or out-of-stock products in e-commerce, though it is incremental as it builds on existing encoder-decoder and GNN methods.
The paper tackles the cold start problem in multi-horizon time series forecasting by using graph neural networks as data augmentation to enhance encoder-decoder models, demonstrating improved performance on datasets with up to 2 million products and substantial gains for cold start items.
Encoder-decoder deep neural networks have been increasingly studied for multi-horizon time series forecasting, especially in real-world applications. However, to forecast accurately, these sophisticated models typically rely on a large number of time series examples with substantial history. A rapidly growing topic of interest is forecasting time series which lack sufficient historical data -- often referred to as the ``cold start'' problem. In this paper, we introduce a novel yet simple method to address this problem by leveraging graph neural networks (GNNs) as a data augmentation for enhancing the encoder used by such forecasters. These GNN-based features can capture complex inter-series relationships, and their generation process can be optimized end-to-end with the forecasting task. We show that our architecture can use either data-driven or domain knowledge-defined graphs, scaling to incorporate information from multiple very large graphs with millions of nodes. In our target application of demand forecasting for a large e-commerce retailer, we demonstrate on both a small dataset of 100K products and a large dataset with over 2 million products that our method improves overall performance over competitive baseline models. More importantly, we show that it brings substantially more gains to ``cold start'' products such as those newly launched or recently out-of-stock.