Capstone project · about 90 minutes
Search Engine with TF-IDF Ranking 🔍
Index a document set, rank results by relevance rather than keyword count, then measure whether your ranking is any good.
Every search box you have used is this, scaled up. You will build an inverted index, score with TF-IDF so a word that appears everywhere counts for little, and then do the part most tutorials skip: measure it. Precision@k turns "it looks about right" into a number, and being able to talk about that number is what…
This is a Pro project. Six portfolio projects are free, so you can see how they work before deciding.