Day 46 of 100DaysofML

Recommendation Engines. I was under a lot of pressure to finish this blog because of time constraints but here goes. I’m going to cover the basics of Recommender engines and I shall share the source code in the next couple of days once I’m done working on the project.

I’d recommend watching this short video, just before we get started.

Honestly some of the best recommendation engines we come across and can be easily explained are SPOTIFY and NETFLIX.

What a Recommendation engine does is basically recommend based (i din’t refer to google for that definition :p) on our past visits or past heard or past watched movies.

How is Big Data being used?
Big Data allowed us to do recommendations on a new scale that we did not see before. The most well-known example is how the Google search algorithm. A recommendation system outdoes benchmarking because it does not need an analyst at the end. It reduces Big Data to small data.

The recommender is the application facing component that is responsible for making the recommendations. Mahout supports both user-based recommenders and item-based recommenders via the User Based Recommender and Item Based Recommender interfaces respectively.

Types of Recommender systems

• Content-based: A popular, recommended product has similar characteristics to what a user views or likes.
• Cluster: Recommended products go well together, no matter what other users have done.
• Collaborative: Other users, who like the same products as another user views or likes, will also like a recommended product.

Why are Recommender engines important?
The use of efficient and accurate recommendation techniques is very important for a system that will provide good and useful recommendation to its individual users. A recommender system usually employs data sources to learn more about such preferences, making good use of explicit feedback resulting from diverse evaluation metrics such as “Add To Favorites” for example, or implicit feedback deriving from the number and length of content-based interactions. Within the implicit feedback approach, a basic algorithm despite being more elaborate than the one which generates completely random recommendations, consists of reflecting most popular content, summing up all user activity and recommending most common content in relation to the number and length of visits.

I find the given video really good to get the overall understanding of the recommender engine.

I shall be covering more about the source code in the coming blogs but I’d have to wrap up with a bit today. Thanks for reading. Keep Learning.

Cheers.