Home-grown South African mathematics, statistics and computer science have come together to give us numer.ai, founded by Richard Craib. This site which has come up with a seemingly brilliant idea, allowing anyone free access to otherwise very expensive data, but in such an encrypted form that you don’t know what the data means, but its patterns are preserved. This data is stock market data which you can use to make predictions. The predictions on their own don’t mean anything, so you send these predictions back to numer.ai, and they can apply it to the unencrypted data and make purchases on the stock market based on the most accurate models on their test data.

It’s simple but brilliant. They give you something very expensive for free, and you give them something very valuable for free. The brightest minds in machine learning can then potentially earn big money which would be impossible if it weren’t for the beauty of homomorphic encryption.

Take a look at the video here: