Predicting mean and variance in inventory order decisions

Author:

Chen Li1ORCID,Davis Andrew M.1ORCID,Kim Dayoung2ORCID

Affiliation:

1. Samuel Curtis Johnson Graduate School of Management, SC Johnson College of Business Cornell University Ithaca New York USA

2. Department of Marketing National University of Singapore Singapore Singapore

Abstract

AbstractWe develop a simple forecast‐anchoring model to explain and predict the mean and variance of observed inventory order decisions in a newsvendor problem. The model assumes that people employ a two‐step decision heuristic. In the first step, a behavioral bias may gravitate the decision maker's point forecast toward a random forecast versus a constant unbiased forecast. In the second step, a behavioral bias of the same magnitude may cause the decision maker to treat the point forecast as if it is the mean of potential demand, and then make an upward or downward adjustment depending on the underage and overage costs. We evaluate the performance of this descriptive forecast‐anchoring model across five experimental newsvendor data sets. First, we fit the model to a setting with uniform demand. We then use the corresponding estimates to generate predictions in a secondary data set with uniform demand, as an out‐of‐sample test. We proceed to fit the model to three additional newsvendor data sets, two with normal demand and one with asymmetric two‐point demand. In all cases, the model predicts the mean and variance of inventory order decisions well. We further investigate the profit implications under the forecast‐anchoring model and find that the predictions match well with the experimental data. Through improved predictions, the model can help upstream supply chain parties anticipate inventory order decisions from buyers and improve profitability.

Publisher

Wiley

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3