What question did this study set out to answer?

The aim is to enhance equity return prediction by integrating macroeconomic data with market indicators.

April 22, 2026Open Access

Macro–Market Fusion with Cross-Attention for Equity Return Prediction

JRJanit RajkarnikarUniversity of Southern Mississippi SJSibin JoshiUniversity of Southern Mississippi ZZZhaoxian ZhouUniversity of Southern Mississippi

Key Points

The aim is to enhance equity return prediction by integrating macroeconomic data with market indicators.
Proposed XAttnFusion architecture with three branches for market and macro data integration.
Evaluated on daily SPY returns using purged cross-validation to avoid information leakage.
Addressed look-ahead bias by lagging macroeconomic inputs by two months.
Achieved a mean out-of-sample AUROC of 0.63±0.05, a 27% improvement over random predictions.
Showed an 8.1% improvement over the best concatenation baseline.
Cross-attention consistently outperformed concatenation fusion in tests on QQQ and IWM data.

Abstract

Macroeconomic conditions are widely believed to influence the direction of equity markets, yet most forecasting models either ignore macroeconomic information or incorporate it through a small set of ad hoc predictors. We propose XAttnFusion, a macro–market fusion architecture that jointly learns from high-frequency market data and lower-frequency macroeconomic time series for equity return prediction. The model comprises three branches: a 1D convolutional network that encodes 40-day market windows (price, volume, and technical indicators), a temporal convolutional network that encodes 24-month macro sequences, and a feedforward branch for volume-at-price structure features. These representations are integrated through multi-head cross-attention, in which the current market state queries the macro sequence to produce a fused representation for directional forecasting. We evaluate XAttnFusion on daily SPY returns from 2012 to 2024 using purged cross-validation with a 5-day embargo to prevent information leakage. To address potential look-ahead bias from macroeconomic publication lags, all macro inputs are lagged by two months. The model achieves a mean out-of-sample AUROC of 0.63±0.05, representing a 27% improvement over random and an 8.1% improvement over the best concatenation baseline. In a fair comparison where each model is independently hyperparameter-tuned, cross-attention fusion improves AUROC by 0.047 over concatenation (p=0.031, Wilcoxon signed-rank test). The model also generalizes to QQQ and IWM, where cross-attention consistently outperforms concatenation fusion. Crucially, the model’s discriminative ability is state-dependent, indicating that the value of macro–market fusion is itself conditioned on market structure. Permutation-based feature importance shows that macro and market branches contribute on a comparable scale (approximately 48% and 36%, respectively), so the gains come from jointly fusing two comparably weighted sources rather than from a single dominant input. Our results show that explicitly modeling macro–market interactions with interpretable attention improves predictive accuracy over naive fusion strategies and provides insight into the time-varying relevance of macroeconomic information in financial forecasting and equity market prediction.

AI से पूछें

Bookmark

View Full Paper