The Netflix prize has fascinated me since it was announced and won. Today Netflix engineering has a blog post discussing their recommendations systems that explains why they chose not to implement the prize-winning algorithm. What stuck out to me most was this bit on how important recommendations are to Netflix:

We have adapted our personalization algorithms to this new scenario in such a way that now 75% of what people watch is from some sort of recommendation. We reached this point by continuously optimizing the member experience and have measured significant gains in member satisfaction whenever we improved the personalization for our members. Let us now walk you through some of the techniques and approaches that we use to produce these recommendations.

If you’ve noticed that recommendations have been moved to positions of greater prominence on the Netflix site over time, that’s why. The increased prominence of the recommendations also contributes to the large number of views selected due to recommendations as well, I’m sure.

The rest of the post goes into explaining what factors Netflix feels contribute to an effective recommendations system. This post is pure gold for anybody who’s building similar features.