Improving Accuracy of Recommendation Systems with Deep Learning Models

EasyChair Preprint 8399

Abstract

Recommendation systems have been demonstrated to be an effective strategy for preventing information overload due to the ever-increasing amount of online information. It is impossible to overestimate the effectiveness of recommendation systems, considering their general employment in online applications and their ability to relieve a range of difficulties related to excessive options. For a variety of reasons, including its superior performance in computer vision as well as natural language processing (NLP), deep learning (DL) has gained considerable scholarly interest in recent years but also to its appealing potential to start from scratch and learn how to express features. Deep learning has recently proved its use in information retrieval along with recommendation system research, demonstrating its pervasiveness. The area of recommendation systems that combines deep learning is booming. Deep learning-based recommendation systems are the subject of much current research, which is summarized in this article. A comprehensive analysis of the current status of deep learning-based recommendation models is presented in this research paper. Last but not least, it focuses on current developments and gives new insights on this cutting-edge new industry.

Keyphrases: Convolutional Neural Network, Hybrid Recommendation System, Natural Language Processing, Recommendation Systems, content-based filtering system, deep learning

@booklet{EasyChair:8399,
  author    = {Geetanjali Tyagi and Susmita Ray},
  title     = {Improving Accuracy of Recommendation Systems with Deep Learning Models},
  howpublished = {EasyChair Preprint 8399},
  year      = {EasyChair, 2022}}