---
title: AI vs Naive Portfolio
url: https://www.ml-quant.com/papers/ssrn/4954881/
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 4954881
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4954881
featured: 2024-09-18
citations: unknown
topic: Portfolio & Allocation
---


# AI vs Naive Portfolio

A study found that Google's Gemini 1.5 Flash language model does not significantly outperform basic portfolios or the S&P 500 index in making investment decisions.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4954881
- Identifier: SSRN 4954881
- Released: 2024-09-12
- First featured: Quant Letter No. 66 (2024-09-18): https://www.ml-quant.com/issues/2024-09-18/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Portfolio & Allocation

## Related

- [Sparse spanning portfolios and under-diversification with second-order stochastic dominance](https://www.ml-quant.com/papers/arxiv/2402.01951/): A new method for estimating sparse second-order stochastic spanning suggests no advantage in expanding a sparse opportunity set beyond 45 assets, with the best sparse portfolio investing in 10 sectors.
- [Portfolio optimisation: Bridging the gap between theory and practice](https://www.ml-quant.com/papers/arxiv/2407.00887/): The article suggests a two-stage framework for improving quantitative investing, considering practical issues and new features like futures contracts and borrowing costs.
- [Alternative Data in Active Asset Management](https://www.ml-quant.com/papers/ssrn/4932677/): Alternative data is vital for investment strategies, providing unique insights and competitive advantages, but requires constant adaptation due to its ever-changing nature.
- [On Accelerating Large-Scale Robust Portfolio Optimization](https://www.ml-quant.com/papers/arxiv/2408.07879/): The paper presents an extended approach to solve large-scale robust portfolio optimization problems, showing robust trading performance and significantly reduced computational time.
- [The Concentration Risk Indicator: Raising the Bar for Financial Stability and Portfolio Performance Measurement](https://www.ml-quant.com/papers/arxiv/2408.07271/): The Concentration Risk Indicator (CRI) is a new tool designed to assess risks associated with concentrated portfolios, useful in areas such as insurance risk and product portfolio mixes, especially where wealth is concentrated in few tokens.
- [Delegated Portfolio Management With Random Default](https://www.ml-quant.com/papers/arxiv/2410.13103/): The paper explores the optimal portfolio delegation between an investor and a portfolio manager in the event of a random default time, using mathematical methods and a deep-learning algorithm to study investment decisions and compensation structures.