Human Resource Management Optimization Strategies for Diverse Work Environments Based on Artificial Intelligence DOI Open Access

Min Wu

Applied Mathematics and Nonlinear Sciences, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 1, 2024

Abstract Under the diversified work environment, relationship between employees and enterprises has ushered in new significant changes. How to adapt changes, form a human resource management model, improve performance is an urgent issue. In this paper, we constructed employee turnover pre-analysis measurement model based on XGBoost artificial intelligence, iterated many times during training, generated weak classifier each iteration, trained basis of residuals previous classifier, finally combined all classifiers weighted way, reduced bias accuracy final through continuous completed construction model. The historical data six branches enterprise W are imported into for analysis, F1 values above 0.85, AUCs higher than 0.7, with good prediction performance. top three important influencing characteristics their weights overtime 0.647, monthly income 0.618, interpersonal 0.579. Accordingly, optimization strategies designed applied Enterprise implement reform. After reform, average separation rate been from 2.23% 0.19%, number separations only 7, which 91.86% lower pre-reform period. This study proposes feasible paths modern information technology intelligence-enabled management, diverse environment.

Язык: Английский

Understanding Recruiters’ Acceptance of Artificial Intelligence: Insights from the Technology Acceptance Model DOI Creative Commons
Filomena Almeida, Ana Junça Silva, Sara L. Lopes

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(2), С. 746 - 746

Опубликована: Янв. 14, 2025

The integration of new technologies in professional contexts has emerged as a critical determinant organizational efficiency and competitiveness. In this regard, the application Artificial Intelligence (AI) recruitment processes facilitates faster more accurate decision-making by processing large volumes data, minimizing human bias, offering personalized recommendations to enhance talent development candidate selection. Technology Acceptance Model (TAM) provides valuable framework for understanding recruiters’ perceptions innovative technologies, such AI tools GenAI. Drawing on TAM, model was developed explain intention use tools, proposing that perceived ease usefulness influence attitudes toward AI, which subsequently affect selection processes. Two studies were conducted Portugal address research objective. first qualitative exploratory study involving 100 interviews with recruiters who regularly utilize their activities. second employed quantitative confirmatory approach, utilizing an online questionnaire completed 355 recruiters. findings underscored transformative role recruitment, emphasizing its potential optimize resource management. However, also highlighted concerns regarding loss personal interaction need adapt roles within domain. results supported indirect effect via positive these tools. This suggests is best positioned complementary tool rather than replacement decision-making. insights gathered from perspectives provide actionable organizations seeking leverage Specifically, show importance ethical considerations maintaining involvement ensure balanced effective

Язык: Английский

Процитировано

0

Human Resource Management Optimization Strategies for Diverse Work Environments Based on Artificial Intelligence DOI Open Access

Min Wu

Applied Mathematics and Nonlinear Sciences, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 1, 2024

Abstract Under the diversified work environment, relationship between employees and enterprises has ushered in new significant changes. How to adapt changes, form a human resource management model, improve performance is an urgent issue. In this paper, we constructed employee turnover pre-analysis measurement model based on XGBoost artificial intelligence, iterated many times during training, generated weak classifier each iteration, trained basis of residuals previous classifier, finally combined all classifiers weighted way, reduced bias accuracy final through continuous completed construction model. The historical data six branches enterprise W are imported into for analysis, F1 values above 0.85, AUCs higher than 0.7, with good prediction performance. top three important influencing characteristics their weights overtime 0.647, monthly income 0.618, interpersonal 0.579. Accordingly, optimization strategies designed applied Enterprise implement reform. After reform, average separation rate been from 2.23% 0.19%, number separations only 7, which 91.86% lower pre-reform period. This study proposes feasible paths modern information technology intelligence-enabled management, diverse environment.

Язык: Английский

Процитировано

0