From the course: Building Recommender Systems with Machine Learning and AI

Unlock this course with a free trial

Join today to access over 22,600 courses taught by industry experts.

Measure the performance of SVD recommendations

Measure the performance of SVD recommendations - Python Tutorial

From the course: Building Recommender Systems with Machine Learning and AI

Start my 1-month free trial Buy for my team

Measure the performance of SVD recommendations

“

- [Instructor] So it took a few minutes, but we got some valid results here for our SVD recommender. Our RMSE score is about 0.9, and MAE is about 0.7. That means that on average, our guess of a rating for a given movie for a given user was off by about 0.7 stars. RMSE is higher, meaning that we got penalized for being way off more often than we'd like. Again, remember, higher error metrics are bad. You want these values to be as low as possible if accuracy is your goal. Our hit rate was just about 3%, which actually isn't that bad, considering that only one movie was left out from each user's ratings to test with. But this number by itself is going to be hard to interpret as good or bad until you have other recommenders to compare it against. If we break it down by a rating value, you can see that our hit rates did better at higher rating predictions, which makes sense and is what we want to see. Cumulative hit rate with a 4.0 threshold isn't much lower than the raw hit rate, meaning…

Contents