Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model
📰 ArXiv cs.AI
Researchers propose the Consensus-Bottleneck Asset Pricing Model, a deep learning approach that incorporates analyst consensus for interpretable stock return predictions
Action Steps
- Integrate aggregate analyst consensus into a deep learning model as a structural bottleneck
- Use the bottleneck constraint as an endogenous regularizer to improve out-of-sample predictions
- Evaluate the model's performance using relevant metrics, such as mean absolute error or R-squared
- Refine the model by incorporating additional features or tweaking hyperparameters
Who Needs to Know This
This research benefits data scientists and quantitative analysts on a team, as it provides a novel approach to predicting stock returns using deep learning and analyst consensus, enabling them to make more informed investment decisions
Key Insight
💡 Incorporating analyst consensus as a bottleneck in a deep learning model can improve interpretability and out-of-sample predictions
Share This
💡 New deep learning model uses analyst consensus to predict stock returns!
Key Takeaways
Researchers propose the Consensus-Bottleneck Asset Pricing Model, a deep learning approach that incorporates analyst consensus for interpretable stock return predictions
Full Article
Title: Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model
Abstract:
arXiv:2512.16251v4 Announce Type: replace-cross Abstract: 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 pre
Abstract:
arXiv:2512.16251v4 Announce Type: replace-cross Abstract: 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 pre
DeepCamp AI