Scholarlink

<p>Addressing the issue of student dropout is a significant challenge for governments, particularly in developing countries such as India, Nepal, Bangladesh, and others. This challenge is further complicated by factors such as poverty, natural disasters, and early marriages. High rates of student dropout can have detrimental effects on a country, reducing its economic productivity, widening social inequalities, and perpetuating the cycle of poverty. Addressing dropout issues necessitates comprehensive strategies to cultivate a skilled and educated workforce, promoting societal well-being and global competitiveness. This research begins by applying a Neural Network based model at the cluster (region) level to identify the factors that have the most impact over time on student dropout. It analyses comprehensive data to understand the reasons why students have dropped out and provides corresponding solutions. Subsequently, it employs agglomerative hierarchical clustering to consolidate results from diverse clusters. This approach enables efficient monitoring of the state-level and country-level educational landscape, with the flexibility to drill down to granular levels as needed to identify specific regional challenges. The effectiveness of this approach is validated through the utilization of real-world datasets.</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

DropWrap: A Neural Network Based Automated Model for Managing Student Dropout

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月10日

查看全文
  • Partha Ghosh,
  • Arnab Charit,
  • Hindol Banerjee,
  • Debanwesa Bandhu,
  • Agniv Ghosh,
  • Ankita Pal,
  • Takaaki Goto,
  • Soumya Sen

摘要

Addressing the issue of student dropout is a significant challenge for governments, particularly in developing countries such as India, Nepal, Bangladesh, and others. This challenge is further complicated by factors such as poverty, natural disasters, and early marriages. High rates of student dropout can have detrimental effects on a country, reducing its economic productivity, widening social inequalities, and perpetuating the cycle of poverty. Addressing dropout issues necessitates comprehensive strategies to cultivate a skilled and educated workforce, promoting societal well-being and global competitiveness. This research begins by applying a Neural Network based model at the cluster (region) level to identify the factors that have the most impact over time on student dropout. It analyses comprehensive data to understand the reasons why students have dropped out and provides corresponding solutions. Subsequently, it employs agglomerative hierarchical clustering to consolidate results from diverse clusters. This approach enables efficient monitoring of the state-level and country-level educational landscape, with the flexibility to drill down to granular levels as needed to identify specific regional challenges. The effectiveness of this approach is validated through the utilization of real-world datasets.