Scholarlink

<p>The Over-The-Top (OTT) services sector has seen explosive growth, largely driven by entertainment. However, educational apps have also made significant strides, particularly since the COVID-19 pandemic. This rapid expansion has outpaced scientific documentation, leading to a notable lack of literature for definitive conclusions on industry adoption. This paper addresses this gap by validating extensive primary data (from over 1600 respondents) on OTT educational apps. We tested the data’s functionality with six machine learning algorithms, with the Random Forest method achieving over 98% accuracy. Our findings are expected to be highly beneficial, serving as a landmark study. They’ll set the stage for future research into simulating educational OTT app subscriptions using machine learning, providing a strong foundation for this evolving field.</p>

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

An empirical study of OTT educational apps subscription prediction using various machine learning algorithms

  • 期刊论文

  • 发表日期：

    2025年7月24日

查看全文
  • Monika Sharma,
  • Neha Mishra,
  • Pradeepta Kumar Sarangi,
  • Krishna Kumar Mishra,
  • Rajnish Sharma

摘要

The Over-The-Top (OTT) services sector has seen explosive growth, largely driven by entertainment. However, educational apps have also made significant strides, particularly since the COVID-19 pandemic. This rapid expansion has outpaced scientific documentation, leading to a notable lack of literature for definitive conclusions on industry adoption. This paper addresses this gap by validating extensive primary data (from over 1600 respondents) on OTT educational apps. We tested the data’s functionality with six machine learning algorithms, with the Random Forest method achieving over 98% accuracy. Our findings are expected to be highly beneficial, serving as a landmark study. They’ll set the stage for future research into simulating educational OTT app subscriptions using machine learning, providing a strong foundation for this evolving field.