Intelligent, Item-Based Stereotype Recommender System

Recommender systems (RS) have become key components driving the success of e-commerce,
and other platforms where revenue and customer satisfaction is dependent on the user’s ability
to discover desirable items in large catalogues. As the number of users and items on a platform
grows, the computational complexity, the vastness of the data, and the sparsity problem constitute
important challenges for any recommendation algorithm. In addition, the most widely studied
filtering-based RS, while effective in providing suggestions for established users and items, are
known for their poor performance for the new user and new item (cold start) problems.
Stereotypical modelling of users and items is a promising approach to solving these problems.
A stereotype represents an aggregation of the characteristics of the items or users which can be
used to create general user or item classes. This work propose a set of methodologies for the
automatic generation of stereotypes during the cold-starts. The novelty of the proposed approach
rests on the findings that stereotypes built independently of the user-to-item ratings improve
both recommendation metrics and computational performance during cold-start phases. The
resulting RS can be used with any machine learning algorithm as a solver, and the improved
performance gains due to rate-agnostic stereotypes are orthogonal to the gains obtained using
more sophisticated solvers.
Recommender Systems using the primitive metadata features (baseline systems) as well as
factorisation-based systems are used as benchmarks for state-of-the-art methodologies to assess
the results of the proposed approach under a wide range of recommendation quality metrics. The
results demonstrate how such generic groupings of the metadata features, when performed in a
manner that is unaware and independent of the user’s community preferences, may greatly reduce
the dimension of the recommendation model, and provide a framework that improves the quality
of recommendations in the cold start.