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.

Evaluating the RBM recommender

Evaluating the RBM recommender - Python Tutorial

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

Start my 1-month free trial Buy for my team

Evaluating the RBM recommender

“

- [Instructor] Alight, we've been talking about RBMs for long enough. Let's actually run the thing and see how it does. Select the RBMBakeOff.py file, and take a quick look at it. There's not a lot to talk about. What we're doing is pitting our RBM algorithm with 20 epochs and default hyper parameters against random recommendations. Hit the play button, and go get a cup of coffee, catch up on your messages, whatever you need to do. We did pass true to the evaluate function, so we're going to run all of the top end metrics on everything, which can take quite a bit of time. So pause this video, and resume when you're ready to view the results with me. Okay, there's a lot to digest here. Let's start by looking at the table of all the metrics. The accuracy metrics RMSE and MAE are better than random, but they're not great. We mentioned before that the way we're computing predicted rating values, tend to artificially lower them. The expectation values we end up with don't get any higher…

Contents