Event-driven hypergraph convolutional networks for financial news-based stock selection

Abstract

Stock selection remains one of the most challenging tasks in quantitative trading due to the complex dependencies and dynamic nature of financial markets. Most existing studies rely on predefined inter-stock relations, which may fail to adapt to regime shifts or to incorporate short-horizon spillovers triggered by news. Moreover, there has been limited progress in systematically inferring event-driven relations from economic and financial news headlines and integrating them as higher-order structures for next-day repricing and co-movement. To address these issues, we propose a framework, HERALD (Hypergraph forEvent-basedRepresentation andAggregation ofLatestDaily news), which estimates a set of potentially affected stocks from news headlines and constructs a daily-updated dynamic hypergraph by treating each set as an event-driven hyperedge. HERALD integrates news-induced higher-order relations with structural relations and historical price signals to learn next-day return rankings. Experimental evaluations and backtesting simulations on real-world datasets from the NASDAQ-100 and the S&P 500 indicate that HERALD achieves competitive performance relative to multiple baselines in both profitability-oriented metrics and ranking-quality measures.