依赖关系感知的稀疏神经网络架构用于股票收益预测
Dependence-Informed Sparse Neural Architecture for Stock Return Prediction
浏览论文内容
中文总结 AI 辅助
该研究提出将最大过滤团森林（MFCF）估计的公司特征依赖关系映射到同调神经网络（HNN），用于股票收益预测，HNN预测准确率与基准相当、排序更准确且参数更少。
中文摘要 AI 辅助
使用神经网络进行股票收益预测通常需要选择难以与金融解释关联的深度和隐藏层宽度。我们研究了一种替代方案：用最大过滤团森林（Maximally Filtered Clique Forest, MFCF）估计公司特征间的依赖关系，再将其团结构映射到同调神经网络（Homological Neural Network, HNN）。MFCF的最大团大小K是控制架构复杂度的唯一参数，具有明确的图形意义：它限定了每个最大团中的特征数量，因此限定了网络可表示的最高交互阶数。过滤后的图在训练前就确定了神经网络的深度、层宽度和稀疏连接，取代了单独选择的深度和宽度序列。我们使用94个公司特征，将两种HNN变体应用于1987至2016年美国股票超额收益的年度样本外预测。HNN模型在合并预测准确率上与三层隐藏层基准模型相当，能更准确地对横截面进行排序，且参数数量仅为具有相同诱导层宽度的全连接网络的约1/80。两项结构 ablation 实验表明，稀疏连接和估计的特征分组均对排序优势有贡献，且在多重检验校正后两种效应仍显著。这些发现表明，HNN为将估计的公司特征间依赖关系纳入神经网络架构设计提供了一种实用且可解释的方法。
英文摘要
Using neural networks for stock return prediction typically requires choices about depth and hidden-layer width that are difficult to connect to financial interpretation. We study an alternative: estimate dependence among firm characteristics with a Maximally Filtered Clique Forest (MFCF), then map its clique structure to a Homological Neural Network (HNN). The MFCF maximum clique size K is the only parameter controlling architectural complexity, and it has a clear graphical meaning: it bounds the number of characteristics in each maximal clique and hence the highest interaction order the network can represent. The filtered graph then fixes the neural network's depth, layer widths, and sparse connections before training, in place of a separately chosen depth and width sequence. We apply two HNN variants to annual out-of-sample forecasts of U.S. stock excess returns from 1987 to 2016 using 94 firm characteristics. The HNN models match a three-hidden-layer benchmark on pooled predictive accuracy, rank the cross-section more accurately, and use roughly 80 times fewer parameters than a fully connected network with the same induced layer widths. Two structural ablations indicate that both the sparse connectivity and the estimated grouping of characteristics contribute to the ranking advantage, and both effects remain significant after correcting for multiple testing. These findings show that HNNs offer a practical and interpretable way to incorporate estimated dependence among firm characteristics into neural architecture design.
