Scholarlink

This study explore the potential of data analysis and modeling for precise YouTube video performance forecasting, recognizing YouTube as a pivotal platform for global content dissemination. Examining data from 6 YouTube channels, we employed ARIMA modeling to predict upcoming video performance based on key attributes such as title, publish date, likes, comments, views, and engagement metrics. Our model revealed a mean absolute error of 7.2% and a root mean squared error of 9.1%, underscoring the significance of various video characteristics in predictive accuracy. These findings offer actionable insights for content creators to enhance content and boost engagement. Moreover, the study underscores the necessity for advanced modeling techniques to achieve accurate YouTube video performance forecasting.

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

YouTube Video Performance: Leveraging Data Analysis and Forecasting with ARIMA Modeling for Optimal Engagement

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • K. S. Hemanth,
  • R. Krishna Murthy,
  • B. Muralidhara

摘要

This study explore the potential of data analysis and modeling for precise YouTube video performance forecasting, recognizing YouTube as a pivotal platform for global content dissemination. Examining data from 6 YouTube channels, we employed ARIMA modeling to predict upcoming video performance based on key attributes such as title, publish date, likes, comments, views, and engagement metrics. Our model revealed a mean absolute error of 7.2% and a root mean squared error of 9.1%, underscoring the significance of various video characteristics in predictive accuracy. These findings offer actionable insights for content creators to enhance content and boost engagement. Moreover, the study underscores the necessity for advanced modeling techniques to achieve accurate YouTube video performance forecasting.