Clustering-Based Matrix Factorization

Recommender systems are emerging technologies that nowadays can be found in many applications such as Amazon, Netflix, and so on. These systems help users to find relevant information, recommendations, and their preferred items. Slightly improvement of the accuracy of these recommenders can highly affect the quality of recommendations. Matrix Factorization is a popular method in Recommendation Systems showing promising results in accuracy and complexity. In this paper we propose an extension of matrix factorization which adds general neighborhood information on the recommendation model. Users and items are clustered into different categories to see how these categories share preferences. We then employ these shared interests of categories in a fusion by Biased Matrix Factorization to achieve more accurate recommendations. This is a complement for the current neighborhood aware matrix factorization models which rely on using direct neighborhood information of users and items. The proposed model is tested on two well-known recommendation system datasets: Movielens100k and Netflix. Our experiment shows applying the general latent features of categories into factorized recommender models improves the accuracy of recommendations. The current neighborhood-aware models need a great number of neighbors to acheive good accuracies. To the best of our knowledge, the proposed model is better than or comparable with the current neighborhood-aware models when they consider fewer number of neighbors.

Object Classification by means of Multi-Feature Concept Learning in a Multi Expert-Agent System

Classification of some objects in classes of concepts is an essential and even breathtaking task in many applications. A solution is discussed here based on Multi-Agent systems. A kernel of some expert agents in several classes is to consult a central agent decide among the classification problem of a certain object. This kernel is moderated with the center agent, trying to manage the querying agents for any decision problem by means of a data-header like feature set. Agents have cooperation among concepts related to the classes of this classification decision-making; and may affect on each others' results on a certain query object in a multi-agent learning approach. This leads to an online feature learning via the consulting trend. The performance is discussed to be much better in comparison to some other prior trends while system's message passing overload is decreased to less agents and the expertism helps the performance and operability of system win the comparison.