Morningstar Incorporates Artificial Intelligence into New Ratings

Earlier this month, Morningstar introduced new quantitative ratings that will cover more than 10,000 funds and ETFs. The system will use both machine learning and artificial intelligence to “learn from the rating produced by Morningstar’s analysts.” This according to an article in InvestmentNews.

“Essentially,” the article reports, “the program will adjust its ratings to learn from mistakes—and incorporate improvements—made by its human counterparts.”

The development stems in part from the increased workload experienced by the firm’s analysts, who are becoming “swamped” by the number of funds to evaluate—7,950 fund and 1,853 ETFs, according to the Investment Company Institute. Morningstar now covers 1,800, but with the addition of the quantitative ratings system, that number will rise to 10,000.

While Morningstar has been expanding its fund coverage over recent years, director of quantitative research Timothy Strauts said, “we realized that at some point we can’t hire 1,000 more analysts,” adding, “The model has been in testing the past four years, and we’re comfortable launching it to the world.”

The new capability, which will look back five years on a rolling basis, will provide investors with ratings of gold, silver or bronze with a superscript “q” to identify it as a quantitative rating.