RankGLU:用于横截面股票预测的残差门控得分形成
RankGLU: Residual Gated Score Formation for Cross-Sectional Stock Prediction
AI总结:
针对横截面股票预测中的排序问题,提出RankGLU,一种残差瓶颈门控线性单元,通过保留直接线性得分路径并添加有界乘法分支,实现稳定排序与可控非线性交互,在CSI300上平均IC提升至0.0727。
摘要:
横截面股票预测更接近排序问题而非普通的收益率幅度回归,因为投资组合决策取决于每个交易日内资产的相对排序。现有的时间、图结构和市场条件注意力模型改进了股票表示学习,但最终预测头常被视为次要实现细节。本文认为,在信息系数导向的评估下,得分形成是一个关键瓶颈:过度灵活的头可能拟合不稳定的收益率幅度,而过于线性的头可能未充分利用交叉特征交互。因此,我们开发了RankGLU,一种用于横截面股票排序的残差瓶颈门控线性单元。RankGLU保持直接线性得分路径,并添加有界乘法分支,从而在允许受控非线性交互的同时保留稳定排序路径。该方法在CSI300和CSI800上使用统一协议进行评估,包括横截面得分归一化和IC增强目标。多种子实验表明,在CSI300上,RankGLU在内部对照变体中实现了最强的平均IC,从原始骨干的0.0654±0.0052和排序感知骨干的0.0697±0.0030提升至0.0727±0.0037,且在所有五个种子上一致。其最佳种子结果也超过了相应的基线。消融结果进一步表明,移除GLU预测头会导致测试组件变化中最明显的性能下降。额外的关系路径校准可以产生高的单种子峰值,但其多种子行为不太稳定。证据表明,排序感知的股票模型最可靠地受益于有界残差得分形成,而非不加区分的架构扩展。
英文摘要:
Cross-sectional stock prediction is closer to a ranking problem than to ordinary return-magnitude regression, since portfolio decisions depend on the relative ordering of assets within each trading date. Existing temporal, graph-based, and market-conditioned attention models have improved stock representation learning, yet the final prediction head is often treated as a minor implementation detail. This paper argues that, under information-coefficient-oriented evaluation, score formation is a critical bottleneck: an over-flexible head can fit unstable return magnitude, whereas an overly linear head may underuse cross-feature interactions. We therefore develop RankGLU, a residual bottleneck gated linear unit for cross-sectional stock ranking. RankGLU keeps a direct linear scoring path and adds a bounded multiplicative branch, thereby preserving a stable ordering route while allowing controlled nonlinear interactions. The method is evaluated on CSI300 and CSI800 under a unified protocol with cross-sectional score normalization and an IC-augmented objective. Multi-seed experiments show that, on CSI300, RankGLU achieves the strongest mean IC among the internally controlled variants, improving from 0.0654+/-0.0052 for the original backbone and 0.0697+/-0.0030 for the ranking-aware backbone to 0.0727+/-0.0037, a gain that is consistent across all five seeds. Its best-seed result also exceeds the corresponding baselines. Ablation results further indicate that removing the GLU prediction head causes the clearest degradation among the tested component changes. Additional relation-path calibrations can produce high single-seed peaks, but their multi-seed behavior is less stable. The evidence suggests that ranking-aware stock models benefit most reliably from bounded residual score formation rather than from indiscriminate architectural expansion.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。