What question did this study set out to answer?

The aim is to utilize sentiment data as an active control signal for stock price predictions, enhancing prediction accuracy.

May 15, 2026Open Access

SGA-DCAT: Sentiment-Gated Dual-Stream Cross-Attention Temporal Network for Stock Price Prediction

Key Points

The aim is to utilize sentiment data as an active control signal for stock price predictions, enhancing prediction accuracy.
Developed SGA-DCAT architecture integrating a sentiment-gated LSTM, dual-stream cross-attention, and multi-scale aggregation.
Analyzed stock price movements using sentiment data from FinBERT regarding the NASDAQ-100 index.
Evaluated performance through metrics such as MAPE, RMSE, and MAE, comparing with several baseline methods.
SGA-DCAT achieved a MAPE of 1.40%, RMSE of 217.83, and MAE of 171.58, outperforming multiple baseline models (all p<0.001).
Directional accuracy of 66.93% was reached on the held-out test set.
Results were consistent across different market conditions including bull, bear, and volatile phases.

Abstract

We propose SGA-DCAT (Sentiment-Gated Dual-stream Cross-Attention Temporal Network), an architecture for stock price prediction that treats news sentiment not as a passive input feature but as a control signal that governs the model’s memory dynamics. Most sentiment-augmented methods simply concatenate sentiment scores with price inputs, which implicitly assumes that the relationship between sentiment and price is the same regardless of market conditions. SGA-DCAT departs from this practice in three ways: (1) a sentiment-gated adaptive LSTM cell modulates the forget and input gates directly through sentiment signals so that memory retention varies with market mood; (2) a dual-stream cross-attention mechanism encodes price and sentiment through separate recurrent networks and fuses them via learned attention, keeping modality-specific representations intact; and (3) a multi-scale adaptive aggregation module combines predictions from 5-day, 10-day, and 20-day windows using a gating network conditioned on the current market state. On the NASDAQ-100 index with FinBERT-derived news sentiment, SGA-DCAT achieves a MAPE of 1.40%, RMSE of 217.83, and MAE of 171.58, outperforming Persistence, ARIMA, GARCH, MLP, LSTM, GRU, Transformer, DA-RNN, TFT, and LSTM + FinBERT baselines (all p<0.001, Diebold–Mariano test). In ablation experiments, each component contributes measurably, and SGA-DCAT reaches 66.93% directional accuracy on the held-out test set. Rolling-window evaluation across four non-overlapping temporal folds and regime-specific analysis confirm that these results are robust across bull, bear, and volatile market conditions.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper