Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon

AI-Powered Stock Selection

Save for later
  • 4 min read
  • 12 Jul 2023

article-image

Artificial Intelligence continues to infiltrate every facet of modern life, from daily chores to complex decision-making procedures, including the stock market. The recent advent of AI-powered language models like ChatGPT by OpenAI serves as a notable testament to this statement. The potential of these models transcends conversational prowess, delving into the ability to guide investment decisions.

A case in point is an experiment conducted by Finder.com, an international financial comparison site. The test pitted an AI-constructed portfolio against some of the most renowned investment funds in the United Kingdom, seeing the AI-curated selection outstrip its counterparts. The portfolio, an assortment of 38 stocks picked by ChatGPT, manifested a gain of 4.9% between March 6 and April 28. In comparison, ten top-tier investment funds noted an average decline of 0.8% in the same period. To put this into perspective, the S&P 500 index, an esteemed gauge of the American market, marked a rise of 3%, and the Stoxx Europe 600, its European equivalent, noted a modest increase of 0.5%.

The experiment's dynamics are as intriguing as its outcome. Investment funds aggregate capital from a multitude of investors, a fund manager administering the investment decisions. However, Finder's analysts asked the AI chatbot to construct a stock portfolio based on prevalent selection criteria - low indebtedness and a solid growth trajectory. Noteworthy picks included industry behemoths like Microsoft, Netflix, and Walmart.

This process's ingenuity lies in its accessibility. While AI has pervaded major funds for years, supplementing investment decisions, the advent of ChatGPT has democratized this expertise. Now, the public can use this technology, thereby revolutionizing retail investment.

How dependable are these AI-driven stock predictions? 

A study by the University of Florida supplies an answer. Published in April, the study posits that ChatGPT could forecast specific companies' stock price movements more accurately than some fundamental analysis models.

In fact, the democratization of AI, characterized by models like ChatGPT and BERT, could potentially upend the financial industry. Researchers across the globe have corroborated this sentiment. In two separate studies, researchers found that large language models (LLMs) can enhance stock market and public opinion predictions, evidenced by historical data.

University of Florida professors Alejandro Lopez-Lira and Yuehua Tang further validated this argument in their paper "Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models". They utilized ChatGPT to assess news headlines' sentiment, a metric that has become indispensable for quantitative analysis algorithms employed by stock traders.

Unlock access to the largest independent learning library in Tech for FREE!
Get unlimited access to 7500+ expert-authored eBooks and video courses covering every tech area you can think of.
Renews at ₹800/month. Cancel anytime

Sentiment analysis discerns whether a text, such as a news headline, conveys a positive, neutral, or negative sentiment about a subject or company. This evaluation enhances the accuracy of market predictions.

Lopez-Lira and Tang applied ChatGPT to gauge the sentiment manifested in news headlines. Upon comparing ChatGPT's assessment of these news stories with the subsequent performance of company shares in their sample, they discovered statistically significant predictions, a feat unachieved by other LLMs.

The professors asserted, "Our analysis reveals that ChatGPT sentiment scores exhibit a statistically significant predictive power on daily stock market returns." This statement, substantiated by their findings, shows a strong correlation between the ChatGPT evaluation and the subsequent daily returns of the stocks in their sample. It underscores the potential of ChatGPT as a potent tool for predicting stock market movements based on sentiment analysis.

Author Bio

Julian Melanson is one of the founders of Leap Year Learning. Leap Year Learning is a cutting-edge online school that specializes in teaching creative disciplines and integrating AI tools. We believe that creativity and AI are the keys to a successful future and our courses help equip students with the skills they need to succeed in a continuously evolving world. Our seasoned instructors bring real-world experience to the virtual classroom and our interactive lessons help students reinforce their learning with hands-on activities.

No matter your background, from beginners to experts, hobbyists to professionals, Leap Year Learning is here to bring in the future of creativity, productivity, and learning!