We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), which embeds aggregate analyst consensus as a structural bottleneck, treating professional beliefs as a sufficient statistic for the market's high-dimensional information set. Unlike post-hoc explainability approaches, CB-APM achieves interpretability-by-design: the bottleneck constraint functions as an endogenous regularizer that simultaneously improves out-of-sample predictive accuracy and anchors inference to economically interpretable drivers. Portfolios sorted on CB-APM forecasts exhibit a strong monotonic return gradient, robust across macroeconomic regimes. Pricing diagnostics further reveal that the learned consensus encodes priced variation not spanned by canonical factor models, identifying belief-driven risk heterogeneity that standard linear frameworks systematically miss.
@article{arxiv.2512.16251,
title = {Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model},
author = {Changeun Kim and Younwoo Jeong and Bong-Gyu Jang},
journal= {arXiv preprint arXiv:2512.16251},
year = {2026}
}