研究在竞争环境下过度自信零售商对市场需求的信念存在偏差时的订货决策问题. 在仅知市场需求的均值和支集的情况下, 应用最大绝对后悔最小化准则, 建立多个过度自信零售商的鲁棒订货模型. 证明了具有多个零售商竞争的报童博弈的鲁棒优化~Nash 均衡解的存在性, 并导出了最优决策的封闭表达式. 讨论过度自信行为对零售商最优订货量和期望利润的影响. 数值分析结果表明: 在最小化最大绝对后悔值准则下, 过度自信零售商获得的实际期望利润要低于其获得的信念期望利润; 在两个零售商的非对称博弈情形, 过度自信零售商获得的实际期望利润要高于完全理性零售商获得的期望利润, 并且每个零售商获得的实际期望利润还随其竞争对手的过度自信程度的增加而增加. 过度自信可以使那些在库存可用性上相互竞争的零售商获益.

The paper investigates the ordering decision approach of overconfident retailers taking into account the influence of the retailers' biased belief on the actual demand. We focus on the well-known newsvendor problem in this study, where the distribution of the random demand is only specified by its mean and support. Applying the absolute regret minimization criterion to this problem, a robust ordering model for multiple overconfident retailers is established. We show existence and derive closed-form expressions for the robust optimization Nash equilibrium solution in a competitive newsvendor setting. Then the impact of the retailer's overconfidence on its optimal orderding decisions and the corresponding expected profit are discussed. The numerical study shows that overconfident retailers obtain lower actual expected profits than their belief expected profits under the maximum absolute regret minimization criterion. Moreover, in the asymmetric game between two nonidentical retailers, the actual expected profit obtained by each retailer in the case of overconfidence is higher than that obtained in the case of complete rationality, and the actual expected profit obtained by each retailer also increases with the degree of overconfidence of its competitor. And the actual expected profit for each retailer also increases with respect to the overconfidence level of the retailer's competitor. We find that overconfidence can benefit retailers that compete against one another on inventory availability.