Scholarlink

In today’s society, recommendation systems are critical. Because there is a huge amount of data around us, whether music, book, or movie data, numerous programs or businesses, including Netflix, Amazon, and Spotify, focus on recommendation systems such as music apps. Systems for recommending content are intended to assist viewers by reducing the need for them to choose from a large variety that may number in the thousands or even millions. With the help of the movie lens dataset, this work aims to conduct a study to analyze the effectiveness of machine learning techniques, like K-NN, XG-Boost algorithms with Pearson Correlation Coefficient, and Count Vectorizer model to develop the Con-tent Recommender System for suggesting the movie. The performance of the proposed systems is evaluated in this study using the RMSE of 1.1062 and 1.1089 for KNN and XG-Boost algorithms, respectively.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Content Recommendations Using Machine Learning-Based Approaches

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ajay Indian,
  • Gaurav Meena,
  • Krishna Kumar Mohbey,
  • Bharati Yadav

摘要

In today’s society, recommendation systems are critical. Because there is a huge amount of data around us, whether music, book, or movie data, numerous programs or businesses, including Netflix, Amazon, and Spotify, focus on recommendation systems such as music apps. Systems for recommending content are intended to assist viewers by reducing the need for them to choose from a large variety that may number in the thousands or even millions. With the help of the movie lens dataset, this work aims to conduct a study to analyze the effectiveness of machine learning techniques, like K-NN, XG-Boost algorithms with Pearson Correlation Coefficient, and Count Vectorizer model to develop the Con-tent Recommender System for suggesting the movie. The performance of the proposed systems is evaluated in this study using the RMSE of 1.1062 and 1.1089 for KNN and XG-Boost algorithms, respectively.