---
title: ChatGPT for Portfolio Selection
url: https://www.ml-quant.com/papers/ssrn/4538502/
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 4538502
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4538502
featured: 2023-08-17
citations: unknown
topic: LLMs & Text
---


# ChatGPT for Portfolio Selection

The research shows AI model ChatGPT is effective in selecting stocks from the SP500 index, but not as efficient in assigning optimal weights to portfolio stocks.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4538502
- Identifier: SSRN 4538502
- Released: 2023-08-11
- First featured: Quant Letter No. 12 (2023-08-17): https://www.ml-quant.com/issues/2023-08-17/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: LLMs & Text

## Related

- [ChatGPT-Based Investment Portfolio Selection](https://www.ml-quant.com/papers/arxiv/2308.06260/): The research shows that AI model ChatGPT is useful in selecting stocks from the S&P500 index, but may not be as efficient in determining the best stock weights in a portfolio.
- [Decision-informed Neural Networks with Large Language Model Integration for Portfolio Optimization](https://www.ml-quant.com/papers/arxiv/2502.00828/): The paper combines Large Language Models with decision-focused learning to improve prediction and decision quality in portfolio optimization, outperforming other deep learning models.
- [LLM-Enhanced Black-Litterman Portfolio Optimization](https://www.ml-quant.com/papers/arxiv/2504.14345/): The research investigates the use of large language models for estimating expected stock returns and integrating uncertainty into portfolio optimization via the Black-Litterman framework, comparing the effectiveness of various models.
- [AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions](https://www.ml-quant.com/papers/arxiv/2508.11152/): The article investigates the application and effectiveness of role-based multi-agent AI systems in equity research and portfolio management, including their advantages and challenges.
- [Evolutionary Factor Searching for Sparse Portfolio Optimization Using Large Language Models](https://www.ml-quant.com/papers/arxiv/2507.17211/): The paper presents Evolutionary Factor Search (EFS), a new method that uses large language models to automatically generate and evolve alpha factors for sparse portfolio construction, showing its effectiveness in different market situations.
- [FinRankGRPO: Optimizing LLMs for Listwise Financial Asset Ranking via Group Relative Policy Optimization](https://www.ml-quant.com/papers/arxiv/2609.24175/): Develops a two-stage framework that fine-tunes language models for listwise asset ranking using Spearman rank correlation rewards, achieving a Sharpe ratio of 0.636 on asset allocation.