Leveraging Spatiotemporal Graph Neural Networks for Multi-Store Sales Forecasting
By: Manish Singh, Arpita Dayama
Potential Business Impact:
Predicts store sales better by seeing how stores affect each other.
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.
Similar Papers
Evaluating Spatio-Temporal Forecasting Trade-offs Between Graph Neural Networks and Foundation Models
Machine Learning (CS)
Improves weather forecasts by choosing best sensors.
No One-Model-Fits-All: Uncovering Spatio-Temporal Forecasting Trade-offs with Graph Neural Networks and Foundation Models
Machine Learning (CS)
Improves weather forecasts by using sensor data better.
Multi-Level Service Performance Forecasting via Spatiotemporal Graph Neural Networks
Machine Learning (CS)
Predicts computer system slowdowns before they happen.