Considering momentum spillover effects via graph neural network in option pricing

Abstract

Traditional options pricing relies on underlying asset volatility and contract properties. However, asset volatility is affected by the “lead–lag effects,” known as the “momentum spillover effect.” To address this, we propose a proxy measuring correlated options' influence based on maturity date. Findings indicate that 1-day-lagged proxy indicators positively impact option returns. Furthermore, to capture the dynamic effects of correlated options, we introduce a deep graph neural network-based model (GNN-MS). Empirical results on Shanghai Stock Exchange 50 exchange-traded fund options reveal GNN-MS significantly outperforms classics, enhancing root-mean-square error by at least 8.81%. This study provides novel insights into option pricing considering momentum spillover effects.