---
title: Equity Returns Predictability with Machine Learning
url: https://www.ml-quant.com/papers/repec/fau-fauart-v-74-y-2024-i-2-p-142-190/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:fau:fauart:v:74:y:2024:i:2:p:142-190
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fjournal.fsv.cuni.cz%2Fmag%2Farticle%2Fshow%2Fid%2F1531%3Bh%3Drepec%3Afau%3Afauart%3Av%3A74%3Ay%3A2024%3Ai%3A2%3Ap%3A142-190
featured: 2024-05-22
citations: unknown
topic: ML & AI Methods
---


# Equity Returns Predictability with Machine Learning

Machine learning techniques' predictability of global stock returns decreases over time, but firm-specific characteristics can still be profitable despite transaction costs.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fjournal.fsv.cuni.cz%2Fmag%2Farticle%2Fshow%2Fid%2F1531%3Bh%3Drepec%3Afau%3Afauart%3Av%3A74%3Ay%3A2024%3Ai%3A2%3Ap%3A142-190
- Identifier: RePEc:fau:fauart:v:74:y:2024:i:2:p:142-190
- Released: 2024-05-22
- First featured: Quant Letter No. 50 (2024-05-22): https://www.ml-quant.com/issues/2024-05-22/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods

## Related

- [Reinforcement Learning for Financial Index Tracking](https://www.ml-quant.com/papers/ssrn/4532072/): Reinforcement Learning and Deep RL Method: A new model for tracking financial indices has been proposed, which improves on existing models by including market information variables, exact transaction cost calculation, and new decision variables for cash injection or withdrawal.
- [Execution-Aware Alpha Mining: Teaching LLM Factor Agents to Account for Trading Costs](https://www.ml-quant.com/papers/ssrn/7498983/): The paper builds a closed-loop system where an LLM proposes equity factors penalized for execution costs and shows that accounting for trading costs dramatically improves net performance.
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://www.ml-quant.com/papers/arxiv/2312.00752/): Sequence Modeling: Mamba, a neural network architecture that doesn't use attention or MLP blocks, provides faster inference and better performance in language, audio, and genomics than Transformers.
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://www.ml-quant.com/papers/arxiv/2405.21060/): The research identifies a link between state-space models and Transformers in deep learning, leading to the creation of a faster language modeling architecture, Mamba-2.
- [Octo: An Open-Source Generalist Robot Policy](https://www.ml-quant.com/papers/arxiv/2405.12213/): Octo is a large transformer-based policy for robotic manipulation, trained on a vast dataset, that can be instructed via language or images and adapted to new domains.
- [Mastering Diverse Domains through World Models](https://www.ml-quant.com/papers/arxiv/2301.04104/): Algorithm Mastery: DreamerV3, a universal algorithm, excels in over 150 varied tasks, including diamond collection in Minecraft without human input, expanding the scope of reinforcement learning.