Scholarlink

<p>This study identifies key predictors of Australian school principals’ turnover intention, using a machine learning approach—extreme gradient boosting (XGBoost) with random effects. Drawing on data from 1630 Australian principals across two years, the prediction model includes 89 psychosocial, health-related, and demographic factors. Commitment to the workplace, job satisfaction, and cognitive demands emerged as the strongest predictors of turnover intention. The proposed framework effectively captures hierarchical and non-linear relations in large datasets, outperforming traditional statistical approaches. Findings offer actionable insights for enhancing principal retention by strengthening psychological connection to the workplace and managing cognitive workload. This research also provides valuable implications for policy and practice in designing targeted interventions and driving systemic improvements in educational leadership.</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

Predictive modelling of Australian school principals’ turnover intentions using machine learning with random effects

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月13日

查看全文
  • Jiesi Guo,
  • Danling Huang,
  • Jinran Wu,
  • Hamed Mogouie,
  • Theresa Dicke

摘要

This study identifies key predictors of Australian school principals’ turnover intention, using a machine learning approach—extreme gradient boosting (XGBoost) with random effects. Drawing on data from 1630 Australian principals across two years, the prediction model includes 89 psychosocial, health-related, and demographic factors. Commitment to the workplace, job satisfaction, and cognitive demands emerged as the strongest predictors of turnover intention. The proposed framework effectively captures hierarchical and non-linear relations in large datasets, outperforming traditional statistical approaches. Findings offer actionable insights for enhancing principal retention by strengthening psychological connection to the workplace and managing cognitive workload. This research also provides valuable implications for policy and practice in designing targeted interventions and driving systemic improvements in educational leadership.