Reinforcement Deep Learning Recommender Systems – Part 1

Recommender System

Every day, we always face a huge amount of information available on many means leading to information overloading problems, which makes people feel difficult to make the right decision.

When we surf a shopping website, we have to pass through many more items in the main page. The more items on the list, the harder it becomes to select among them. Understanding the demand, and with the development of many information platforms such as YouTube, Amazon, Netflix or e-commerce, a Recommendation System has been established and improved with the development of machine learning and artificial intelligence.

You can also check posts in the series:

• Part 2: Reinforcement Learning in Recommendation system
• Part 3: Reinforcement Learning based Recommendation System

Recommendation System

Definition

Recommender System (RS) is a software tool and algorithm that helps users find their interested items. It replies on the prediction of their item preferences or their rating on the items. RS is established to deal with the “long tail problem”. When users just only have attention to the highlighted items in a specific domain, they left behind many items that may be useful for them. In fact, the number of these items is very huge. This situation happens frequently in supermarkets or in e-commercial websites.

 

Method

The method for recommender system is divided into three type as the taxonomy below: content-based methods, collaborative filtering methods, and hybrid methods. The hybrid one is a combination of two previous methods.

 

Content-based methods:

These methods make recommendations based on a description of the item, a profile of the user’s preferences, and the relation between them. You can use it for a large number of users. It doesn’t any data from other users and each recommendation is a specific user. However, this method needs a huge knowledge about a domain. For example, information about the rating of users for an item. This means that we need to handle knowledge-crawling by hand.

Collaborative filtering methods:

There are two types of this method: memory-based and model-based. While the memory-based method is based on the similarities between users or items in the interaction observation (user-user or item-item), model-based method uses some algorithms such a Clustering algorithms, Matrix Factorization-based algorithm and Deep-Learning methods to learn the users/items behavior from the interaction matrix. Different with the above methods, this model no need a huge domain knowledge and it can help use discover more about their interest by recommending an item from a similar user interested with it. However, this model cannot deal with the new items, or cold-start problem, but there are some ways to address this problem or using content-based method. Other problem is that this system is hard to include some side-feature for items that can help the recommender system is more trustworthy.

 

Hybrid methods:

The combination of Content-based and collaborative filtering methods. It takes advantage of the advantages of each method to minimize their drawbacks of them.

 

Useful resources:

• Introduction to recommender systems | by Baptiste Rocca
• Recommender Systems with Python series | by Nikita Sharma

Medium link: How Will Reinforcement Learning Based Recommendation System Be In The Future — Part 1: Recommender System