Addressing Algorithmic Bias in AI‐Driven HRM Systems: Implications for Strategic HRM Effectiveness
基于动态能力视角，研究了HR算法偏见管理能力的三个维度（数据、模型、部署偏见管理能力），发现它们通过AI赋能的高绩效HR实践正向影响战略HRM有效性，对HR从业者应对AI带来的伦理与运营挑战有指导意义。
ABSTRACT AI and machine learning algorithms are revolutionising the modern workplace by transforming HR functions to deliver superior outcomes for both employees and organisations. However, research shows that these algorithms often fail to deliver optimal HR solutions, primarily due to inherent biases. Developing capabilities to overcome algorithmic biases is critical for firms, as these biases present significant challenges to fairness and inclusivity in HR decision‐making, ultimately impacting the effectiveness of HR practices. To address this challenge, our study, grounded in the dynamic capability perspective, presents a model to address algorithmic biases in people management and achieve superior strategic HR outcomes. To test our theoretical model, we collected survey data using a two‐wave, time‐lagged approach from HR professionals and employees working in firms within the Australian financial and insurance industries. The key findings reveal three critical dimensions of HR algorithmic bias management capability: data bias, model bias, and deployment bias management capabilities, which significantly influence AI‐enabled high‐performance HR practices and, in turn, positively impact strategic HRM effectiveness. Our novel findings on the dimensions of HR bias management capability contribute to advancing the dynamic capability view in HRM research. They also offer a comprehensive bias management framework that allows HR professionals to address the strategic, ethical, and operational challenges emerging from the use of AI‐augmented HR practices in the dynamic workplace, helping sustain a competitive advantage.