A data-driven newsvendor problem: From data to decision

Huber, Jakob ; Müller, Sebastian ; Fleischmann, Moritz ; Stuckenschmidt, Heiner

DOI: https://doi.org/10.2139/ssrn.3090901
URL: https://ssrn.com/abstract=3090901
Document Type: Working paper
Year of publication: 2017
The title of a journal, publication series: SSRN Working Paper Series
Place of publication: Rochester, NY
Publication language: English
Institution: Business School > ABWL u. Logistik (Fleischmann 2009-)
School of Business Informatics and Mathematics > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-)
Subject: 330 Economics
Keywords (English): inventory , newsvendor , artifcial neural networks , quantile regression
Abstract: Retailers that order perishable items are required to make ordering decisions for hundreds of products on a daily basis. This task is non-trivial because the risk of ordering too much or too little is associated with overstocking costs and unsatisfied customers. Traditionally, this problem is solved in a two-step procedure. First, the parameters of a given demand distribution are estimated, and second, an optimization problem based on this distribution is solved to obtain the order quantity. However, in reality, the true demand distribution is almost never known to the decision maker. Therefore, we present a novel solution method based on Artificial Neural Networks and Quantile Regression that does not require the assumption of a specifc demand distribution. We provide an empirical evaluation of our method with point-of-sales data for a large German bakery chain. We find that our method outperforms well-established standard approaches in most cases.

Dieser Eintrag ist Teil der Universitätsbibliographie.

Metadata export


+ Search Authors in

+ Page Views

Hits per month over past year

Detailed information

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item