Scholarlink

<p>In today’s fast-paced and technology-driven world, the gap between the skills taught in educational institutions and the requirements of the industry has become a significant challenge. Industries constantly evolve, demanding new competencies and up-to-date knowledge from the workforce. This research aims to develop a machine learning-driven framework to dynamically match industry skill requirements with educational curricula and generate adaptive course recommendations. Data collection from diverse sources, including job portals, industry reports, company career pages, and labor market analysis, captures the latest skill demands across multiple sectors. The framework utilizes an advanced machine learning Dynamic Termite Life Cycle Optimizer-driven Euclidean-Support Vector Machine (DTLC-Euclidean SVM) to predict both current and emerging skill demands in the job market. By analyzing patterns in graduate skillsets and employer requirements, the system identifies gaps and aligns educational offerings accordingly. The dynamic matching algorithm employs similarity metrics and k-Means Clustering techniques map industry needs to existing course content, while an automated course generation module suggests new or updated courses to address identified skill shortages. The overall performance accuracy (96.8%), precision (97.6%), recall (96.2%), and f1-score (97.3%), further establish its robustness and reliability in bridging the skill gap. This data-driven approach enables continuous curriculum adaptation, fostering stronger alignment between academia and industry. Finally, the framework supports educators and policymakers in developing responsive, targeted educational programs that prepare students for real-world career opportunities, enhancing employability and addressing the demands of a rapidly evolving labor market.</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

Machine learning-driven dynamic matching of industry-education demands and course generation algorithms

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月28日

查看全文
  • Rui Zhu

摘要

In today’s fast-paced and technology-driven world, the gap between the skills taught in educational institutions and the requirements of the industry has become a significant challenge. Industries constantly evolve, demanding new competencies and up-to-date knowledge from the workforce. This research aims to develop a machine learning-driven framework to dynamically match industry skill requirements with educational curricula and generate adaptive course recommendations. Data collection from diverse sources, including job portals, industry reports, company career pages, and labor market analysis, captures the latest skill demands across multiple sectors. The framework utilizes an advanced machine learning Dynamic Termite Life Cycle Optimizer-driven Euclidean-Support Vector Machine (DTLC-Euclidean SVM) to predict both current and emerging skill demands in the job market. By analyzing patterns in graduate skillsets and employer requirements, the system identifies gaps and aligns educational offerings accordingly. The dynamic matching algorithm employs similarity metrics and k-Means Clustering techniques map industry needs to existing course content, while an automated course generation module suggests new or updated courses to address identified skill shortages. The overall performance accuracy (96.8%), precision (97.6%), recall (96.2%), and f1-score (97.3%), further establish its robustness and reliability in bridging the skill gap. This data-driven approach enables continuous curriculum adaptation, fostering stronger alignment between academia and industry. Finally, the framework supports educators and policymakers in developing responsive, targeted educational programs that prepare students for real-world career opportunities, enhancing employability and addressing the demands of a rapidly evolving labor market.