用大模型预测员工离职，效果优于传统方法。
Can Large Language Model Predict Employee Attrition?
- 用微调的GPT-3.5分析员工数据，捕捉离职潜在线索。
- 准确率91%，召回率94%，F1达92%，超越传统模型。
- 适合想用AI提升留任策略的企业与研究者。
员工流失给组织带来巨大成本，传统统计方法难以应对现代职场复杂性。机器学习虽有进展，但大语言模型（LLM）通过理解员工沟通细节，可识别微妙离职信号。本研究基于IBM HR Analytics Attrition数据集，对比微调后的GPT-3.5与逻辑回归、KNN、SVM、决策树、随机森林、AdaBoost、XGBoost等传统模型的预测性能。结果表明，微调的GPT-3.5模型在预测员工流失上表现更优：精确率0.91，召回率0.94，F1-score达0.92；而表现最好的传统模型SVM仅得F1-score 0.82，随机森林与XGBoost为0.80。这证明了GPT-3.5能有效挖掘离职风险中的复杂模式，为组织提供更精准的留任决策支持，凸显大模型在人力资源管理中的应用价值。
原文摘要 · Abstract (English)
Employee attrition poses significant costs for organizations, with traditional statistical prediction methods often struggling to capture modern workforce complexities. Machine learning (ML) advancements offer more scalable and accurate solutions, but large language models (LLMs) introduce new potential in human resource management by interpreting nuanced employee communication and detecting subtle turnover cues. This study leverages the IBM HR Analytics Attrition dataset to compare the predictive accuracy and interpretability of a fine-tuned GPT-3.5 model against traditional ML classifiers, including Logistic Regression, k-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, AdaBoost, and XGBoost. While traditional models are easier to use and interpret, LLMs can reveal deeper patterns in employee behavior. Our findings show that the fine-tuned GPT-3.5 model outperforms traditional methods with a precision of 0.91, recall of 0.94, and an F1-score of 0.92, while the best traditional model, SVM, achieved an F1-score of 0.82, with Random Forest and XGBoost reaching 0.80. These results highlight GPT-3.5's ability to capture complex patterns in attrition risk, offering organizations improved insights for retention strategies and underscoring the value of LLMs in HR applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。