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

Unlock this course with a free trial

Join today to access over 22,700 courses taught by industry experts.

Dive deeper into content-based recommendations

Dive deeper into content-based recommendations - Python Tutorial

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

Start my 1-month free trial Buy for my team

Dive deeper into content-based recommendations

“

- [Instructor] As an exercise, try modifying contentKandNrecommender.py to use genre, release year, and mise en scene data independently. Which produces the best accuracy, and which produces the most satisfying results subjectively to you? If you have lots of time, you can pass true into the evaluate function in contentrecs.py to compute more evaluation metrics to work with. I'll go over my results in the next slides so hit pause if you don't want any spoilers. So here are the results I got by trying each content attribute out independently. As far as accuracy goes, genre is the winner, and qualitatively, I think genre is the winner as well. You can see that release year just ended up finding the the year this user liked films from the best and recommended whatever it could find from that year. Since we only have release dates down to the year level, what really happened here is every movie from 1994 was tied for first place. So it's kind of arbitrary which ones made it into the top…

Contents