Researchers at the University of Auckland are using artificial intelligence to assess the true value of companies based on profitability, efficiency, growth, risk, and more.
In a paper published in the Journal of Accounting Research, business school academics Helen Lu and Paul Geertsema show that machine learning algorithms can provide more accurate stock valuations than traditional methods.
The company’s machine learning method outperforms traditional models in its valuation accuracy, and stocks identified as undervalued tend to rise in price, allowing investors to take no additional risk. You will have the opportunity to profit.
Not only that, but Lu and Geertsema have also developed machine learning algorithms to help experts identify competitors when traditional methods are inadequate. This is especially useful in countries like New Zealand where finding obvious peers can be difficult, says Lu.
Determining a company’s value requires many subjective choices, so stock prices can be subject to human bias, Lu said. This is why this kind of machine learning methodology is revolutionary.
According to Dr. Lu, industry professionals often evaluate companies against others in the same industry, but this process of determining which companies are peers can be subject to bias. There is evidence that practitioners strategically select peers to achieve desired assessment outcomes.
“If what is being evaluated is a software company, industry professionals typically look for peers in the technology industry and ideally find a few companies offering similar products, but the process is It’s very subjective, because what exactly is the “technology industry” and how can you definitively determine if several companies are comparable… perhaps pricing power and growth potential Should gender be considered as well? Skilled professionals often follow a ‘gut feeling’ that can be subject to personal bias.
To minimize such problems, researchers trained and utilized what are known as tree-based machine learning models. These models use company fundamentals to automatically figure out the best way to assign companies to the various “leaves” of the tree. As a result, businesses that are often assigned to the same leaf can be viewed as close peers with similar fundamentals. Conversely, companies that are rarely assigned to the same leaf have different fundamentals.
The researchers’ models analyzed a large sample of US common stocks listed on the NYSE, NASDAQ, and AMEX between January 1980 and December 2019. These models can be extended to stock markets around the world.
According to Lu, their approach not only produced more accurate valuations than traditional models across companies over time, but the valuations were closer to the true value of the companies.
end
For interviews and comments from the authors, please contact:
sophie.boladeras@auckland.ac.nz, 022 4600 388
Paper: Relative Evaluation by Machine Learning
Dr. Helen Lu is a Fintech Leader in the Master of Business Analytics program and Dr. Paul Giasema teaches MBA in Financial Machine Learning and Data Analytics, both at the University of Auckland.
