Could mutual fund managers achieve performance improvements by "hiring" artificial intelligence (AI) analysts? In their May 2025 working draft entitled "The Shadow Price of 'Public' Information", Ed deHaan, Chanseok Lee, Miao Liu and Suzie Noh estimate the value of an AI stock picking analyst by having it exploit public data to improve mutual fund holdings. Specifically, they:
- Each year train the AI (random forest model) on an expanding window of 170 stock market, accounting, analysts and macroeconomic inputs.
- For each mutual fund each quarter:
- Have the AI make limited improvement/replacement picks similar to the type of stocks already in the fund, with the goal of maximizing benchmark-adjusted returns. The benchmark for each fund consists of a portfolio of stocks with similar characteristics.
- Require the AI to mimic original fund and holdings sizes.
- Quantify the profit difference between original and AI-improved portfolios.
They also consider matched portfolios selected completely (not partial replacement) by the AI analyst. Using data for 3,337 active/diversified U.S. equity mutual funds during 1990 through 2020, and for firm characteristics and trading data of all U.S. listed common stocks, macroeconomic variables, analyst forecasts, credit ratings and market/firm sentiment data starting 1980, they find that:
Read this study free
The rest of this study: 260 words.
Enter your email and we’ll send you a link to this article. 3 premium articles a month, no password or card.
Or join for everything
- 181 premium articles in Investing Expertise
- 3,514 research articles in all
- Monthly signals for both strategies
- The Research Assistant
Cancel anytime