Recommendation Systems : A Comparative Analysis of Classical and Deep Learning Approaches

Abstract

Recommendation systems bring in the lion’s share of e-business. Personalised recommendations make it easy for the user to take decisions quickly since the top recommended items will be produced after analysing user preferences, past user actions and current market trends. A very good recommendation engine is necessary for the e-business to ensure huge revenue. In this paper we quantitatively analyse the research works done on recommendation systems in the last decade(2010-2020) and qualitatively analyze the current state of the art(2018-2021). We find that towards the end of the last decade, deep learning based recommendations attracted more attention due to their ability to make more accurate recommendations.