MENDNet: Memory-Enhanced Dependency Network for Multistock Movement Prediction.

AgentPEN: A Prediction-Explanation Network for Sequential Stock Movement via LLMs and Recurrent Generation

Event-driven hypergraph convolutional networks for financial news-based stock selection

Stock selection remains one of the most challenging tasks in quantitative trading due to the complex dependencies and dynamic nature of financial markets. Most existing studies rely on predefined inter-stock relations, which may fail to adapt to regime shifts or to incorporate short-horizon spillovers triggered by news. Moreover, there has been limited progress in systematically inferring event-driven relations from economic and financial news headlines and integrating them as higher-order structures for next-day repricing and co-movement. To address these issues, we propose a framework, HERALD (Hypergraph forEvent-basedRepresentation andAggregation ofLatestDaily news), which estimates a set of potentially affected stocks from news headlines and constructs a daily-updated dynamic hypergraph by treating each set as an event-driven hyperedge. HERALD integrates news-induced higher-order relations with structural relations and historical price signals to learn next-day return rankings. Experimental evaluations and backtesting simulations on real-world datasets from the NASDAQ-100 and the S&P 500 indicate that HERALD achieves competitive performance relative to multiple baselines in both profitability-oriented metrics and ranking-quality measures.

MSATE-Net: A Multi-Scale Attention-Enhanced Bidirectional Temporal Network for Stock Index Forecasting

This study proposes MSATE-Net for next-day stock index forecasting. The model combines parallel one-dimensional convolutions with receptive fields of 3, 7, and 15 trading days, a bidirectional LSTM operating entirely inside a historical lookback window, sample-dependent temporal attention, and a residual regularized prediction head. Here, “bidirectional” denotes paired processing of the same observed window; it does not assert time-reversal invariance of financial prices or access to observations after the forecast origin. The globally learned attention temperature controls overall selectivity and is not described as a regime-specific adaptive parameter. Experiments use S&P 500, CSI 300, and Nikkei 225 data; persistence and drift benchmarks; recent forecasting architectures; five-seed uncertainty estimates; expanding-window tests; return and directional metrics; and Diebold–Mariano comparisons. The revised evidence supports lower price-level errors, while directional and significance results are mixed across markets. Because a separate model is fitted in each market, the findings establish cross-market consistency rather than transfer learning.

Attention Integration Strategies in MLP-Based Stock Movement Prediction: Effects on Performance, Stability, and Interpretability

Stock movement prediction remains challenging because financial data are non-stationary and noisy. While attention mechanisms are widely used to enhance neural networks, how different attention integration strategies affect performance and training stability has not been systematically examined. We present a multi-seed empirical analysis of MLP-based models under three integration strategies—plain MLP, naively inserted self-attention, and residual attention—together with LSTM and Transformer baselines, evaluating 16 configurations on 10 CSI 300 and 10 S&P 500 stocks under a strictly forward-looking label, a purged chronological split, and early stopping: 1600 runs in total. Interleaved naive attention, in which self-attention output replaces the forward-path representation, collapses to degenerate single-class predictions in every run on both markets, whereas strategies that preserve the original representation collapse no more often than attention-free models; this difference is decisive after correction for multiple comparisons (Holm-adjusted p < 10−3). In contrast, no significant accuracy differences are detected among families, including the baselines, once collapsed runs are excluded, and unconditional balanced accuracy is within 0.01 across all non-degenerate families—consistent with the limited short-horizon predictability implied by market efficiency theory. A Jacobian analysis of the attention block, verified by training diagnostics, attributes the collapse to a rank-one attention matrix that compresses the forward representation to a single scalar unless the original representation is retained. A multi-seed analysis further shows that attention weight interpretations are not reproducible across random seeds and should be validated across repeated runs. These findings show that integration strategy and representation preservation—not the mere inclusion of attention—determine whether attention-augmented lightweight models train reliably.

A Stock Market Price Prediction Model Integrating a CNN–Transformer Dual-Channel Dynamic Attention Architecture

Stock market price prediction remains a persistent challenge owing to the non-stationarity, high noise content, and intricate spatiotemporal dependencies that characterize financial time series. Existing approaches typically excel at either local pattern extraction or long-range dependency modeling, yet seldom reconcile both within a unified framework. This paper introduces a CNN–Transformer dual-channel architecture equipped with a dynamic attention fusion module for stock price forecasting. The convolutional channel applies hierarchical dilated convolutions to distill fine-grained local patterns from multi-indicator sequences while suppressing high-frequency noise. Simultaneously, the Transformer channel employs multi-head self-attention to capture long-distance temporal correlations and regime-shift dynamics. A learnable gating mechanism then fuses the two feature streams by adaptively weighting local detail against global trend information according to market conditions. Experiments conducted on four real-world stock datasets spanning the S&P 500, CSI 300, NASDAQ Composite, and Hang Seng Index show that the proposed model reduces mean absolute error by 9.7–15.3% and root mean square error by 9.5–13.8% relative to competitive baselines including LSTM, CNN–LSTM, Informer, and PatchTST. Ablation studies further indicate that both channels and the fusion module contribute to prediction accuracy, and the architecture remains effective across markets with differing volatility profiles.

A Hybrid Model for Stock Index Forecasting Integrating Multi-Scale Local Attention and State-Space Modeling

Stock index forecasting is essential for financial market analysis and risk monitoring, yet it remains challenging because index price series are nonlinear, non-stationary, and driven by heterogeneous market factors. Existing methods remain limited in preserving local price patterns, capturing multi-scale local dependencies, and integrating attention-derived structures with long-range state-space representations. To address these limitations, we propose AG-SSM, an attention-guided state-space model for multi-step stock index forecasting. The model first uses variable-wise patch embedding to construct local semantic units, which are then processed by the AG-SSM architecture for temporal representation learning. Its core block integrates dual-path local attention (DPLA), S4D-based state-space feature generation, attention-guided aggregation (AGA), and gated update (GU). Specifically, DPLA combines sliding and dilated local attention to capture contiguous and sparsely distributed dependencies, while AGA reuses local attention maps to refine state-space features, thereby coupling local market structures with long-range sequential dynamics. Experiments on six stock index datasets (SSE, SZSE, SMESE, SP500, DJIA, and NIKKEI225) under one-, five-, ten-, and fifteen-step forecasting horizons show that AG-SSM achieves the lowest horizon-averaged MAPE on all six datasets while maintaining competitive performance across other metrics and individual horizons. Averaged over five independent runs, the horizon-averaged MAPE values are 1.5466%, 2.2173%, 2.2293%, 1.4373%, 1.2995%, and 1.8738% on the six datasets, respectively. Ablation studies, state-space variant comparisons, sensitivity analyses, and statistical tests further support the effectiveness and robustness of the proposed framework.