---
title: AI-Powered Direct Indexing: Exploring Thematic Universes for Enhanced Risk-Adjusted Returns
url: https://www.ml-quant.com/papers/ssrn/4977007/
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 4977007
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4977007
featured: 2025-12-01
citations: 0
topic: ML & AI Methods
---


# AI-Powered Direct Indexing: Exploring Thematic Universes for Enhanced Risk-Adjusted Returns

The research presents FINDALL, a search engine that effectively identifies relevant stocks for direct indexing, outperforming traditional ETFs with lower costs.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4977007
- Identifier: SSRN 4977007
- Released: 2024-11-14
- First featured: Quant Letter No. 121 (2025-12-01): https://www.ml-quant.com/issues/2025-12-01/
- Citations (Semantic Scholar): 0
- Published in: not yet
- Topic: ML & AI Methods

## Related

- [Quantifying A Firm's AI Engagement: Constructing Objective, Data-Driven, AI Stock Indices Using 10-K Filings](https://www.ml-quant.com/papers/doi/10-1016-j-techfore-2024-123965/): A new method using natural language processing (NLP) has been suggested for classifying AI stocks, providing a cost-effective alternative that outperforms existing AI-themed ETFs.
- [AI Impact on Investments](https://www.ml-quant.com/papers/ssrn/5224162/): AI technology adoption by mutual fund managers leads to superior returns and lower expenses, especially in discretionary funds.
- [Generalized Factor Neural Network Model for High-dimensional Regression](https://www.ml-quant.com/papers/arxiv/2502.11310/): A novel method combining non-parametric regression, factor models, and neural networks has been introduced, showing effectiveness in predicting equity ETF indices prices and macroeconomic data.
- [Machine Learning in Fund Classification](https://www.ml-quant.com/papers/ssrn/4794900/): The paper uses machine learning to categorize hedge funds, finding that those classified as systematic yield higher excess returns.
- [Boosting Fund Performance](https://www.ml-quant.com/papers/ssrn/4697785/): Mutual funds that match their investments with similar benchmark peers like the S&P 500 index yield higher returns and experience less volatility.
- [Sharpening Sharpe Analysis with Machine Learning](https://www.ml-quant.com/papers/ssrn/4650859/): The research shows that over 95% of mutual funds have multidimensional investment styles, and those that change their styles often outperform their new style benchmarks.