Welcome to GuruPredictor.com!

Have you ever wanted to predict what new stocks your favorite investors are likely to buy next? This website uses machine learning to let you do that.* Using it, you can find many of those new stock buys before they happen by going through a manageable list of predicted stocks.**

You can also use this website to find more investors with a similar style to an investor you like, or to find more stocks similar to a stock you like. GuruPredictor's algorithms can find similarities that aren't based on the obvious stuff like company sector or financial ratios. Click one of the links below to get started:

Find stocks a particular investor might like.

Find more investors with a style similar to a particular investor.

Find more stocks similar to a particular stock.

The fine print:
*See the About tab for more information on how this works.
**Based on tests of past data. Of course, past performance doesn't predict future results.

This tab tells you what stocks a particular investor is predicted likely to buy, excluding ones they already hold. Start typing an investor name (ex. Icahn) below, then select from the drop down list.

Suggested use: Check the lists for investors you like. If a new stock comes up that you're not familiar with, it might be worth checking out.

Omit most popular:

This tab finds stocks similar to a specified one. This search can find similarities that are not based on standard data like financial ratios. Start typing a company name (ex. Exxon) below, then select from the drop down list.

Suggested use: Find new stocks similar to those you like.

This tab finds investors with a style similar to a specified one. Start typing an investor name (ex. Buffett) below, then select from the drop down list.

Suggested use: Find new investors with a similar style to those you like.

About GuruPredictor.com

How this works: This site uses a modified version of a type of machine learning algorithm called a recommender system. This is what, for example, Netflix might use to recommend new movies to you. The algorithm is applied to data from 13F forms that large investors are required to file with the SEC after each quarter, detailing what stocks they hold as of the end of the quarter.

How this was tested: I've tested how well this algorithm predicts "unexpected" big buys, in which an investor goes from owning none or less than 1% of a stock in one quarter, to 5% or more in the next quarter. On a sample of about 2,000 of these unexpected buys over the past two years, I've found that a large fraction appear near the top of the predicted lists for each investor (the lists on the "Find stocks for ..." tab). For example, about a third of the unexpected buys appear in the top 25 predicted names for each investor.

Gurupredictor was created by Isaac Dimitrovsky, Ph.D. For inquiries, please use the form below:

Your email or phone: