Scholarlink

In the field of educational statistics, one of the most important tasks is student classification for the purposes of performance prediction or the detection of potential dropouts. It is essential for educational institutions to be able to make accurate projections of their students’ future achievements and success. Because it serves as the measure by which education systems globally are evaluated, the accomplishment of students is extremely important to those who work in education. In addition, kids who stop attending school contribute to a reduction in this efficiency; therefore, identifying these pupils as early as possible is essential. As a result, arranging educational data in the appropriate categories is of the utmost importance. The recent advances in technology have made it possible to use a broad variety of classification strategies to educational records in a way that is both effective and efficient. It is necessary to investigate a greater number of techniques and methods suitable for this sort of activity. The amount of data that is being gathered by educational institutions is growing at a rapid rate, and so is the breadth of topics that are being covered. Investigating the usefulness of unconventional methods is an interesting endeavor. This article presents a deep auto encoder based technique for forecasting students academic performance. Experimental results have shown that the accuracy of autoencoder in predicting academic performance is 98.5%.

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

Implementing a Deep Learning Approach for Forecasting Student Acedemic Performance

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Shazia Asif,
  • Manjula Jain,
  • Meenakshi,
  • Khaled A. Z. Alyamani,
  • Sami A. Morsi,
  • Abhishek Raghuvanshi

摘要

In the field of educational statistics, one of the most important tasks is student classification for the purposes of performance prediction or the detection of potential dropouts. It is essential for educational institutions to be able to make accurate projections of their students’ future achievements and success. Because it serves as the measure by which education systems globally are evaluated, the accomplishment of students is extremely important to those who work in education. In addition, kids who stop attending school contribute to a reduction in this efficiency; therefore, identifying these pupils as early as possible is essential. As a result, arranging educational data in the appropriate categories is of the utmost importance. The recent advances in technology have made it possible to use a broad variety of classification strategies to educational records in a way that is both effective and efficient. It is necessary to investigate a greater number of techniques and methods suitable for this sort of activity. The amount of data that is being gathered by educational institutions is growing at a rapid rate, and so is the breadth of topics that are being covered. Investigating the usefulness of unconventional methods is an interesting endeavor. This article presents a deep auto encoder based technique for forecasting students academic performance. Experimental results have shown that the accuracy of autoencoder in predicting academic performance is 98.5%.