# Enhancing Portfolio Optimization with Deep Learning Insights

arXiv: https://arxiv.org/abs/2601.07942 · HTML: https://mlsanity.com/paper/2601.07942/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 7 of 7)

- [Temporal Relational Ranking for Stock Prediction](https://mlsanity.com/paper/1809.09441/) (2018)
- [Enhancing Time Series Momentum Strategies Using Deep Neural Networks](https://mlsanity.com/paper/1904.04912/) (2019)
- [Financial Trading as a Game: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1807.02787/) (2018)
- [Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture](https://mlsanity.com/paper/2112.08534/) (2021)
- [Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection](https://mlsanity.com/paper/2105.13727/) (2021)
- [Machine Learning Optimization Algorithms & Portfolio Allocation](https://mlsanity.com/paper/1909.10233/) (2019)
- [U-CNNpred: A Universal CNN-based Predictor for Stock Markets](https://mlsanity.com/paper/1911.12540/) (2019)

## Abstract (arXiv)

Our work focuses on deep learning (DL) portfolio optimization, tackling challenges in long-only, multi-asset strategies across market cycles. We propose training models with limited regime data using pre-training techniques and leveraging transformer architectures for state variable inclusion. Evaluating our approach against traditional methods shows promising results, demonstrating our models' resilience in volatile markets. These findings emphasize the evolving landscape of DL-driven portfolio optimization, stressing the need for adaptive strategies to navigate dynamic market conditions and improve predictive accuracy.