Algorithm aversion during disruptions: The case of safety stock
研究供应链中断时企业是否拒绝算法推荐而依赖主观判断，发现算法厌恶确实存在且算法决策优于人工，并基于访谈提出解释理论。
Algorithm aversion occurs when organizations or individuals reject optimal analytical decision support in favour of informal, subjective decisions. This phenomenon has been observed in many practical decision-making scenarios and is generally believed to negatively impact decision quality. However, its existence and effect in volatile supply chain environments has not been empirically tested in the literature. Safety stock buffering demand volatility is an important decision in supply chain management, making it an ideal lens to observe algorithm aversion. In this paper, we empirically investigate algorithm aversion behaviour in the context of safety stock settings. We collect data from a case retail company across a range of stockkeeping units (SKUs), encompassing both pre-disruption and post-disruption time stages with varying levels of volatility. We introduce a simulation model to determine whether algorithm aversion exists for safety stock decisions and to assess how algorithm adoption and adaptation affects performance. Our findings indicate that algorithm aversion occurs during supply chain disruptions, with algorithmic decisions significantly outperforming human judgment. Based on interview results and theories of information systems, we propose a theory to explain and generalize the above findings. This theory attributes algorithm aversion behaviour to reduced sense of fitness among algorithm users and lack of slack resources for both users and developers. It also offers insights into how the adoption and adaptation of algorithms influence decision performance during disruptive events.