The Data-Driven Newsvendor Problem: New Bounds and Insights
Consider the newsvendor model, but under the assumption that the underlying demand distribution is not known as part of the input. Instead, the only information available is a random, independent sample drawn from the demand distribution. This paper analyzes the sample average approximation (SAA) ap...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute for Operations Research and the Management Sciences (INFORMS)
2017
|
| Online Access: | http://hdl.handle.net/1721.1/111091 https://orcid.org/0000-0002-1994-4875 https://orcid.org/0000-0002-0888-9030 |
| _version_ | 1826210152722726912 |
|---|---|
| author | Levi, Retsef Perakis, Georgia Uichanco, Joline |
| author2 | Sloan School of Management |
| author_facet | Sloan School of Management Levi, Retsef Perakis, Georgia Uichanco, Joline |
| author_sort | Levi, Retsef |
| collection | MIT |
| description | Consider the newsvendor model, but under the assumption that the underlying demand distribution is not known as part of the input. Instead, the only information available is a random, independent sample drawn from the demand distribution. This paper analyzes the sample average approximation (SAA) approach for the data-driven newsvendor problem. We obtain a new analytical bound on the probability that the relative regret of the SAA solution exceeds a threshold. This bound is significantly tighter than existing bounds, and it matches the empirical accuracy of the SAA solution observed in extensive computational experiments. This bound reveals that the demand distribution’s weighted mean spread affects the accuracy of the SAA heuristic. |
| first_indexed | 2024-09-23T14:44:43Z |
| format | Article |
| id | mit-1721.1/111091 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:44:43Z |
| publishDate | 2017 |
| publisher | Institute for Operations Research and the Management Sciences (INFORMS) |
| record_format | dspace |
| spelling | mit-1721.1/1110912024-06-28T14:32:32Z The Data-Driven Newsvendor Problem: New Bounds and Insights Levi, Retsef Perakis, Georgia Uichanco, Joline Sloan School of Management Levi, Retsef Perakis, Georgia Consider the newsvendor model, but under the assumption that the underlying demand distribution is not known as part of the input. Instead, the only information available is a random, independent sample drawn from the demand distribution. This paper analyzes the sample average approximation (SAA) approach for the data-driven newsvendor problem. We obtain a new analytical bound on the probability that the relative regret of the SAA solution exceeds a threshold. This bound is significantly tighter than existing bounds, and it matches the empirical accuracy of the SAA solution observed in extensive computational experiments. This bound reveals that the demand distribution’s weighted mean spread affects the accuracy of the SAA heuristic. National Science Foundation (U.S.) (Grant DMS-0732175) National Science Foundation (Grant CMMI-0846554) United States. Air Force Office of Scientific Research (Award FA9550-08-1-0369) United States. Air Force Office of Scientific Research (Award FA9550-11-1-0150) National Science Foundation (U.S.) (Grant CMMI- 0824674) National Science Foundation (U.S.) (Grant CMMI-0758061) 2017-08-31T19:43:15Z 2017-08-31T19:43:15Z 2015-10 2010-08 Article http://purl.org/eprint/type/JournalArticle 0030-364X 1526-5463 http://hdl.handle.net/1721.1/111091 Levi, Retsef, et al. “The Data-Driven Newsvendor Problem: New Bounds and Insights.” Operations Research 63, 6 (December 2015): 1294–1306 © 2015 Institute for Operations Research and the Management Sciences (INFORMS) https://orcid.org/0000-0002-1994-4875 https://orcid.org/0000-0002-0888-9030 en_US http://dx.doi.org/10.1287/opre.2015.1422 Operations Research Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute for Operations Research and the Management Sciences (INFORMS) Shikha Sharma |
| spellingShingle | Levi, Retsef Perakis, Georgia Uichanco, Joline The Data-Driven Newsvendor Problem: New Bounds and Insights |
| title | The Data-Driven Newsvendor Problem: New Bounds and Insights |
| title_full | The Data-Driven Newsvendor Problem: New Bounds and Insights |
| title_fullStr | The Data-Driven Newsvendor Problem: New Bounds and Insights |
| title_full_unstemmed | The Data-Driven Newsvendor Problem: New Bounds and Insights |
| title_short | The Data-Driven Newsvendor Problem: New Bounds and Insights |
| title_sort | data driven newsvendor problem new bounds and insights |
| url | http://hdl.handle.net/1721.1/111091 https://orcid.org/0000-0002-1994-4875 https://orcid.org/0000-0002-0888-9030 |
| work_keys_str_mv | AT leviretsef thedatadrivennewsvendorproblemnewboundsandinsights AT perakisgeorgia thedatadrivennewsvendorproblemnewboundsandinsights AT uichancojoline thedatadrivennewsvendorproblemnewboundsandinsights AT leviretsef datadrivennewsvendorproblemnewboundsandinsights AT perakisgeorgia datadrivennewsvendorproblemnewboundsandinsights AT uichancojoline datadrivennewsvendorproblemnewboundsandinsights |