Show HN: Related Website Finder Experiment Thingy
2 by marginalia_nu | 0 comments on Hacker News.
Been messing with cosine similarity and decided to try calculating nearest neighbors over the entire link graph for the marginalia search engine. Turns out that you can just bruteforce that in a day or two. And the results are pretty good. One drawback is that depending on if you're looking at an older website, a lot of the links are dead. The deduplication isn't great either.
2 by marginalia_nu | 0 comments on Hacker News.
Been messing with cosine similarity and decided to try calculating nearest neighbors over the entire link graph for the marginalia search engine. Turns out that you can just bruteforce that in a day or two. And the results are pretty good. One drawback is that depending on if you're looking at an older website, a lot of the links are dead. The deduplication isn't great either.