O'Reilly logo

Building Recommendation Engines by Suresh Kumar Gorakala

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Evaluating collaborative filtering

We have seen how to build recommendations using collaborative filtering approaches. But the key thing is to build efficient recommendations. Evaluating the accuracy of the recommender models - what we built - is a very crucial step in building recommendation engines. In this section, we will look at how to evaluate both user-based recommenders and item-based recommenders.

Mahout provides components that enable us to evaluate the accuracy of the recommendation models we have built so far. We can evaluate how closely our recommendation engine estimates the preferences against the actual preference values. We can instruct Mahout to use part of the original training data to set aside and use this test dataset in order ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required