Forecasting Equity Correlations with Hybrid Transformer Graph Neural Network

TL;DR

This paper introduces a hybrid Transformer-Graph Neural Network model for 10-day ahead stock correlation forecasting, improving accuracy and basket trading strategies during market stress.

Contribution

It develops a novel THGNN architecture combining temporal transformers and graph attention for regime-aware, interpretable correlation forecasts.

Findings

Reduces correlation forecasting error compared to historical estimates.

Enhances basket trading strategies during market stress.

Provides interpretable, regime-aware correlation predictions.

Abstract

This paper studies forward-looking stock-stock correlation forecasting for S\&P 500 constituents and evaluates whether learned correlation forecasts can improve graph-based clustering used in basket trading strategies. We cast 10-day ahead correlation prediction in Fisher-z space and train a Temporal-Heterogeneous Graph Neural Network (THGNN) to predict residual deviations from a rolling historical baseline. The architecture combines a Transformer-based temporal encoder, which captures non-stationary, complex, temporal dependencies, with an edge-aware graph attention network that propagates cross-asset information over the equity network. Inputs span daily returns, technicals, sector structure, previous correlations, and macro signals, enabling regime-aware forecasts and attention-based feature and neighbor importance to provide interpretability. Out-of-sample results from 2019-2024 show that the proposed model meaningfully reduces correlation forecasting error relative to rolling-window estimates. When integrated into a graph-based clustering framework, forward-looking correlations produce adaptable and economically meaningfully baskets, particularly during periods of market stress. These findings suggest that improvements in correlation forecasts translate into meaningful gains during portfolio construction tasks.