Incorporating Interactive Facts for Stock Selection via Neural Recursive ODEs

TL;DR

This paper introduces StockODE, a novel neural recursive ODE-based model for stock selection that captures continuous stock dynamics and domain-aware dependencies, significantly improving investment performance metrics.

Contribution

The paper proposes a new continuous-time stock selection model using neural recursive ODEs and hierarchical hypergraphs to incorporate explicit and implicit domain dependencies.

Findings

Up to 18.57% improvement in Sharpe Ratio

Effective modeling of continuous stock dynamics

Enhanced consideration of domain interdependencies

Abstract

Stock selection attempts to rank a list of stocks for optimizing investment decision making, aiming at minimizing investment risks while maximizing profit returns. Recently, researchers have developed various (recurrent) neural network-based methods to tackle this problem. Without exceptions, they primarily leverage historical market volatility to enhance the selection performance. However, these approaches greatly rely on discrete sampled market observations, which either fail to consider the uncertainty of stock fluctuations or predict continuous stock dynamics in the future. Besides, some studies have considered the explicit stock interdependence derived from multiple domains (e.g., industry and shareholder). Nevertheless, the implicit cross-dependencies among different domains are under-explored. To address such limitations, we present a novel stock selection solution -- StockODE, a latent variable model with Gaussian prior. Specifically, we devise a Movement Trend Correlation module to expose the time-varying relationships regarding stock movements. We design Neural Recursive Ordinary Differential Equation Networks (NRODEs) to capture the temporal evolution of stock volatility in a continuous dynamic manner. Moreover, we build a hierarchical hypergraph to incorporate the domain-aware dependencies among the stocks. Experiments conducted on two real-world stock market datasets demonstrate that StockODE significantly outperforms several baselines, such as up to 18.57% average improvement regarding Sharpe Ratio.