STN-TGAT: Top-K Portfolio Construction via Prior-Guided Graph Attention with Learnable Soft-Threshold Sparsification
For quantitative finance practitioners, this work provides a practically effective framework for portfolio construction that aligns with real-world trading conditions.
The paper proposes STN-TGAT, a model that integrates temporal Transformer and graph attention with soft-threshold sparsification for stock ranking and portfolio construction. It achieves consistent outperformance over benchmarks in predictive accuracy and portfolio returns under realistic settings including Top-5 selection and transaction costs.
This paper tackles the problem of stock ranking and portfolio construction under realistic investment settings by jointly modeling temporal dynamics and cross-sectional dependencies. We propose the Soft-Threshold NMI-prior Transformer Graph Attention Network (STN-TGAT), which integrates a temporal Transformer with a Graph Attention Network to capture long-horizon sequential patterns and dynamic inter-stock relationships. An NMI-based prior graph combined with a soft-threshold sparsification mechanism enhances structural robustness by mitigating noisy correlations while preserving informative connections. The portfolio formation process incorporates practical considerations, including Top-5 selection within the Top-50 $S\&P$ 500 constituents, explicit weight allocation, and transaction cost adjustment, thereby aligning the evaluation with real-world trading conditions. Empirical results on real-world data demonstrate that STN-TGAT consistently outperforms benchmark models from predictive accuracy and investment profitability measured by portfolio returns. These findings suggest that combining decision-aligned training with adaptive relational modeling provides a coherent and practically effective framework for data-driven portfolio construction.