Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model
This work addresses the problem of opaque machine learning models in finance for investors and researchers, offering a novel approach that is incremental in integrating human expertise with AI.
The paper tackles the challenge of combining deep learning's predictive power with interpretability in stock return prediction by introducing the Consensus-Bottleneck Asset Pricing Model, which uses analyst consensus as a bottleneck to achieve an out-of-sample R2 improvement and an annualized Sharpe ratio of 1.44.
We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), a framework that reconciles the predictive power of deep learning with the structural transparency of traditional finance. By embedding aggregate analyst consensus as a structural "bottleneck", the model treats professional beliefs as a sufficient statistic for the market's high-dimensional information set. We document a striking "interpretability-accuracy amplification effect" for annual horizons, the structural constraint acts as an endogenous regularizer that significantly improves out-of-sample R2 over unconstrained benchmarks. Portfolios sorted on CB-APM forecasts exhibit a strong monotonic return gradient, delivering an annualized Sharpe ratio of 1.44 and robust performance across macroeconomic regimes. Furthermore, pricing diagnostics reveal that the learned consensus captures priced variation only partially spanned by canonical factor models, identifying structured risk heterogeneity that standard linear models systematically miss. Our results suggest that anchoring machine intelligence to human-expert belief formation is not merely a tool for transparency, but a catalyst for uncovering new dimensions of belief-driven risk premiums.