Scholarlink

One of the biggest issues in higher education across the globe is student dropout rates, with broad-reaching consequences for individuals, institutions, and society. A student’s early withdrawal from a program of higher education without a degree hinders academic advancement, restricts employment prospects, and has economic and social costs. Student dropout prediction is a crucial application of educational data mining, with the goal of identifying or predicting attrition patterns in colleges and universities. This can assist institutions in instituting timely interventions. Solutions outlined below, using multiple linear regression-based prediction and frequent pattern growth for mining associative patterns in dropout data, are given. These strategies tackle reasons for dropping out and trends by using past and transactional student data.

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

Integrating Frequent Pattern Mining and Predictive Analytics for Student Dropout Prediction

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Rajesh Sharma,
  • Vijay Dev,
  • Preetvanti Singh

摘要

One of the biggest issues in higher education across the globe is student dropout rates, with broad-reaching consequences for individuals, institutions, and society. A student’s early withdrawal from a program of higher education without a degree hinders academic advancement, restricts employment prospects, and has economic and social costs. Student dropout prediction is a crucial application of educational data mining, with the goal of identifying or predicting attrition patterns in colleges and universities. This can assist institutions in instituting timely interventions. Solutions outlined below, using multiple linear regression-based prediction and frequent pattern growth for mining associative patterns in dropout data, are given. These strategies tackle reasons for dropping out and trends by using past and transactional student data.