Published Paper Details:

Recommender systems are a subclass of information filtering systems. These systems are specialized software components, which usually make part of a larger software system, but can also be standalone tools. A recommender system's main goal is to provide the user software suggestions for items that can be useful. The suggestions are related to different decision-making mechanisms, different techniques, such as, what product to buy, what movie to watch, or what vacation to reserve. In the context of recommender systems, the general term "item" refers to what the system is actually recommending to its users. The paper presents the development and the comparison of multiple recommendation systems, capable of making item suggestions, based on user, item and user-item interaction data, using different machine learning algorithms. Also, the paper deals with finding different ways of using machine learning models to create recommendation systems, training, evaluating and comparing the different methods in order to provide a general but accurate solution for ranking prediction.