---
title: Machine Learning for Portfolio Performance
url: https://www.ml-quant.com/papers/ssrn/4655091/
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: SSRN 4655091
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4655091
featured: 2023-12-06
citations: unknown
topic: Portfolio & Allocation
---


# Machine Learning for Portfolio Performance

The study introduces a method to determine the impact of individual factors on portfolio performance, providing insights into the economic value of return predictability in machine learning models.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4655091
- Identifier: SSRN 4655091
- Released: 2023-11-29
- First featured: Quant Letter No. 28 (2023-12-06): https://www.ml-quant.com/issues/2023-12-06/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Portfolio & Allocation

## Related

- [Active ETFs Cloned from Mutual Funds: Competing for Investor Flows](https://www.ml-quant.com/papers/ssrn/4653702/): The research indicates that less transparent active ETFs do not affect mutual fund investor flows, instead, the reputation of the cloned mutual funds helps the new ETFs attract more flows.
- [On Optimal Tracking Portfolio in Incomplete Markets: The Reinforcement Learning Approach](https://www.ml-quant.com/papers/arxiv/2311.14318/): The paper uses capital injection to solve an optimal tracking portfolio problem in incomplete market models, showcasing the q-learning algorithm's performance.
- [Improved Data Generation for Enhanced Asset Allocation: A Synthetic Dataset Approach for the Fixed Income Universe](https://www.ml-quant.com/papers/arxiv/2311.16004/): The study presents a method for creating synthetic datasets to evaluate asset allocation methods and build portfolios within the fixed income universe.
- [Missing values handling for machine learning portfolios](https://www.ml-quant.com/papers/arxiv/2207.13071/): The study shows that using cross-sectional means for simple imputation is effective in dealing with missing values in machine learning-constructed portfolios, as complex imputations can cause underperformance due to estimation noise.
- [Portfolio Optimization Model for Supporting Venture Capital Decision-Making](https://www.ml-quant.com/papers/ssrn/4660000/): The article introduces a model for improving venture capital investment portfolios, taking into account high risk and uncertain future values, using bootstrapping and mixed-integer linear programming.
- [Partial Information in a Mean‐Variance Portfolio Selection Game](https://www.ml-quant.com/papers/arxiv/2312.04045/): The article investigates how limited information affects investors' wealth and systemic risk, using a model where investors adjust their strategies based on their wealth compared to others.