Sorry if that was confusing. The most of the experiments in the paper are around U.S. flu rate predictions using a compressed version of Google Search.

Perhaps you could update to the paper title then? This doesn't seem like it should have the prefix 'Show HN' - Show HN is for something you've made that other people can play with. HN users can try it out, give you feedback, and ask questions in the thread. https://news.ycombinator.com/showhn.html

And guidelines request the original title, unless it is misleading or linkbait https://news.ycombinator.com/newsguidelines.html

Yeah sorry, already updated it!

Scales well to large unlabeled datasets and outperforms existing methods.

Uses a simple non-constrastive method that doesn't rely on explicit positives and negatives.