F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data

arXiv:2406.16221v1 Announce Type: new
Abstract: Demand prediction is a crucial task for e-commerce and physical retail businesses, especially during high-stake sales events. However, the limited availability of historical data from these peak periods poses a significant challenge for traditional forecasting methods. In this paper, we propose a novel approach that leverages strategically chosen proxy data reflective of potential sales patterns from similar entities during non-peak periods, enriched by features learned from a graph neural networks (GNNs)-based forecasting model, to predict …

abstract arxiv availability businesses challenge commerce cs.ai cs.gr cs.lg data demand demand forecasting e-commerce econ.em events forecasting gnn historical data however meta meta-learning novel paper peak prediction retail sales stake stat.me type