Neural Networks and Evolutionary Algorithms Based Approaches for Engineering Recommendation Systems – A Comprehensive Review

Recommendation systems are the subset of data filtering techniques and focus on providing personalized suggestions to the users. The systems rely on the data to provide insightful suggestions. Over the years, recommendation system has gained huge prominence in boosting e-commerce platforms, and online personalized services to users. Along with their popularity, these systems also face challenges such as data sparsity, time constraints, and scalability. As a result, various approaches are opted along with the traditional techniques to optimize the process. This paper reviews the various approaches followed in engineering the recommendation systems and analyzes their efficiencies. The approaches focus primarily on understanding the involvement of neural networks and evolutionary algorithms and their performance compared to other systems involved with approaches like clustering techniques, linear-based techniques, probabilistic models, etc. This paper also provides insights into the various hybrid approaches followed by the different recommender systems involving neural networks and evolutionary algorithms.