Leveraging Spatiotemporal Graph Neural Networks for Multi-Store Sales Forecasting
It addresses sales forecasting for interconnected retail stores, offering a robust modeling choice with demonstrated performance gains, though it is incremental as it applies an existing method to a specific domain.
This work tackled multi-store retail sales forecasting by evaluating spatiotemporal Graph Neural Networks (STGNNs) against traditional baselines, showing that STGNNs achieved the lowest overall forecasting error, including improvements in Normalised Total Absolute Error and P90 MAPE, using data from 45 Walmart stores.
This work evaluates the effectiveness of spatiotemporal Graph Neural Networks (GNNs) for multi-store retail sales forecasting and compares their performance against ARIMA, LSTM, and XGBoost baselines. Using weekly sales data from 45 Walmart stores, we construct a relational forecasting framework that models inter-store dependencies through a learned adaptive graph. The proposed STGNN predicts log-differenced sales and reconstructs final values through a residual path, enabling stable training and improved generalisation. Experiments show that STGNN achieves the lowest overall forecasting error, outperforming all baselines in Normalised Total Absolute Error, P90 MAPE, and variance of MAPE across stores. Analysis of the learned adjacency matrix reveals meaningful functional store clusters and high-influence nodes that emerge without geographic metadata. These results demonstrate that relational structure significantly improves forecast quality in interconnected retail environments and establishes STGNNs as a robust modelling choice for multi-store demand prediction.