Scholarlink

This study investigates long-term trends in admissions to science, technology, engineering, and mathematics programs at the Universidad de Guadalajara (2010–2025), with a particular focus on engineering. Using institutional data, we analyzed key indicators—including applicant volume, admission thresholds, and selectivity ratios—through artificial intelligence-based techniques. Principal Component Analysis revealed structural differences in program competitiveness, while anomaly detection algorithms identified careers with irregular behavior. Segmented regression models captured the impact of the COVID-19 pandemic, showing post-2020 volatility and declining interest in engineering despite growing demand in health-related fields. A seasonal autoregressive integrated moving average forecast further predicts a downward trend in applicant numbers over the next three years. These results provide insight into vocational misalignment and highlight the need for strategic intervention in career orientation and capacity planning. All data and code are publicly available to support reproducibility and future applications.

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

Interpretable Machine Learning for Engineering Admission Trends at the University of Guadalajara

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Anyer Jacobo,
  • Yuritzi Mondragón,
  • Juan Carlos Kelly,
  • Jose A. Morales,
  • German Preciat

摘要

This study investigates long-term trends in admissions to science, technology, engineering, and mathematics programs at the Universidad de Guadalajara (2010–2025), with a particular focus on engineering. Using institutional data, we analyzed key indicators—including applicant volume, admission thresholds, and selectivity ratios—through artificial intelligence-based techniques. Principal Component Analysis revealed structural differences in program competitiveness, while anomaly detection algorithms identified careers with irregular behavior. Segmented regression models captured the impact of the COVID-19 pandemic, showing post-2020 volatility and declining interest in engineering despite growing demand in health-related fields. A seasonal autoregressive integrated moving average forecast further predicts a downward trend in applicant numbers over the next three years. These results provide insight into vocational misalignment and highlight the need for strategic intervention in career orientation and capacity planning. All data and code are publicly available to support reproducibility and future applications.