ChatGPT Prompts for Stock Selection from a Hedge Fund Manager

In a recent Business Insider interview, CEO of private equity firm Praefinium Alpesh Patel shared his experiment with using ChatGPT for stock selection. He also provides two prompts that they use to increase performance and reliability.

Alpesh Patel's Experiment with ChatGPT for Stock Selection

Incorporating AI into Stock Picking

  • Alpesh Patel, CEO of Praefinium, leverages ChatGPT and Julius AI to analyze stocks on the NYSE and Nasdaq.
  • Patel had previous success with a proprietary stock-scoring and picking algorithm called Alpesh Patel Special Edition algorithm shows up to 1,214% return since inception until 2021.
  • Now, AI and LLMs are adding a new layer to their stock selection and investment research process.

Using ChatGPT's Large Language Model

  • Patel experimented with GPT-4's LLM, using prompts to pick promising stocks.
  • Julius AI was used to interpret and analyze data for over 6,800 stocks.
  • Two prompts were carefully crafted to solicit AI recommendations for top stocks.

Prompt 1

💡
As a knowledgeable stock market analyst with expertise similar to Warren Buffett, your task is to analyze the given data and provide recommendations for the top 10 stocks to invest in. Please consider the following guidelines for your response: 1. Base your recommendations on thorough analysis and understanding of the literature and factors that influence stock markets. Incorporate your knowledge of market trends, company fundamentals, and investor sentiment. 2. Evaluate the given data carefully, considering factors such as financial statements, historical performance, industry trends, and any other relevant information that may impact the stocks' potential. 3. When providing your recommendations, explain your reasoning behind each selection, highlighting key indicators or factors that support your decision. Consider discussing the stocks' growth potential, competitive advantages, and any risks or challenges they may face. Please note that while you should aim to provide the best 10 stocks based on your analysis, the stock market is complex and subject to volatility. Your recommendations should be well-reasoned and grounded in data, but remember that investing always carries some level of risk.

Prompt 2

💡
I want you to look at all the data columns and using not just What Warren Buffett may consider important, but the leading academic literature on stock price movements, as well as weighing these factors or metrics by their importance in the data, tell which 10 are the best stocks for the next 6 months.

Findings and Insights

  • Initial tests reveal that GPT-4 can confirm investor homework and provide insights based on given data.
  • Proper prompt crafting and review of calculations are critical steps.

Comparative Analysis with Human Decision

  • Patel's experimentation with Julius AI showed a selection of top 10 stocks, with an average return of 23.20%.
  • Patel manually picked 69 stocks with an average return of 20.54%.
  • He emphasizes that neither human nor AI guarantees success in the stock market.

Challenges and Considerations

  • Further work and testing are required to fully leverage ChatGPT in stock selection.
  • Proper data feeding, question framing, and utilization of machine learning models are essential for precise outcomes.

Our take
Patel's experiments with GPT-4 and large language models demonstrates a novel approach to stock selection, which in my opinion will only continue to accelerate over the next few years.

While LLMs certainly aren't a crystal ball, there's no question they can play a major role in the investment research process, from automating data analysis, asking questions about large corpus of text and filings, and more. As Patel notes, there's no substitute for thoughtful human analysis, but those that use AI and LLMs will likely have an edge in their research process.

Read the full article.