Book Recommendation System Using Machine Learning

EasyChair Preprint 10012

Abstract

Users may utilize book recommendations to find and search for books on the internet. Given the enormous number of objects and descriptions for the user's needs, this recommendation system will assist the user in selecting the book that matches the description. Rating, Reviews, Description, and Author are all factors that influence recommendation systems.

The efficacy of Book Recommendation Systems heavily relies on the classifier used. Thus, it is crucial to develop a precise classifier to enhance the performance of recommendation systems. Among various supervised learning approaches and algorithms, Decision Tree Classifiers stand out due to their high accuracy, rapid classification speed, robust learning ability, and simple construction.

This paper proposes a Decision Tree-Based recommendation system framework. Other notable supervised learning approaches and algorithms include Naïve Bayes, Random Forest, Logistic Regression, and K-Nearest Neighbor.

Keyphrases: Decision Tree Classifier, Recommender System, XGBoost, logistic regression, machine learning

@booklet{EasyChair:10012,
  author    = {Anant Duhan and N Arunachalam},
  title     = {Book Recommendation System Using Machine Learning},
  howpublished = {EasyChair Preprint 10012},
  year      = {EasyChair, 2023}}