FinD³: A Dual 3D State Space Model with Dynamic Hypergraph for Financial Stock Prediction

The financial market plays a crucial role in the modern economy by influencing capital allocation, corporate valuation, and investor behavior. However, its complex dependencies and non-stationary dynamics present significant challenges for financial stock prediction. Previous predictive approaches are typically categorized into Univariate Time Series (UTS) and Multivariate Time Series (MTS) paradigms. UTS methods overlook both cross-feature and cross-stock influences, while MTS methods can only capture one of these simultaneously. Although some recent approaches claim to model 3D Multivariate Time Series (3D-MTS) dependencies, they often discard substantial information and fail to capture the dynamics of the stock market. To address these limitations, we propose FinD³, a Financial 3D model using Dual cubic state spaces and Dynamic hypergraphs. To extract the inherent complex relationships in 3D-MTS, we propose a novel Dual Cubic State Space Model (DCSSM) to capture both cross-feature and cross-stock patterns. Furthermore, to more accurately reflect the dynamics of the stock market, we present an Evolving Hypergraph Attention (EHA) module, which captures dynamic changes in financial markets and updates the hypergraph based on a priori hypergraph. Experimental results demonstrate that FinD³ achieves state-of-the-art performance in quantitative trading performance on two real-world stock market datasets, offering a promising solution to practical quantitative trading challenges. The code is available at: https://github.com/decisionintelligence/FinD3.