Using Neural Networks to Guide Data-Driven Operational Decisions

43 Pages Posted: 26 Sep 2022 Last revised: 27 Dec 2022

See all articles by Ningyuan Chen

Ningyuan Chen

University of Toronto - Rotman School of Management

Saman Lagzi

Wilfrid Laurier University - Lazaridis School of Business & Economics

Joseph Milner

University of Toronto - Rotman School of Management

Date Written: September 12, 2022

Abstract

We propose to use Deep Neural Networks to solve data-driven stochastic optimization problems. Given the historical data of the observed covariate, taken decision, and the realized cost in past periods, we train a neural network to predict the objective value as a function of the decision and the covariate. Once trained, for a given covariate, we optimize the neural network over the decision variable using gradient-based methods because the gradient and the Hessian matrix can be analytically computed. We characterize the performance of our methodology based on the generalization bound of the neural network. We show strong performance on two signature problems in operations management, the newsvendor problem and the assortment pricing problem.

Keywords: Deep Neural Networks, data-driven, newsvendor problem, product pricing

Suggested Citation

Chen, Ningyuan and Lagzi, Saman and Milner, Joseph, Using Neural Networks to Guide Data-Driven Operational Decisions (September 12, 2022). Available at SSRN: https://ssrn.com/abstract=4217092 or http://dx.doi.org/10.2139/ssrn.4217092

Ningyuan Chen

University of Toronto - Rotman School of Management ( email )

Saman Lagzi (Contact Author)

Wilfrid Laurier University - Lazaridis School of Business & Economics ( email )

Waterloo, Ontario N2L 3C5
Canada

HOME PAGE: http://samanlagzi.com

Joseph Milner

University of Toronto - Rotman School of Management ( email )

105 St. George Street
Toronto, Ontario M5S 3E6 M5S1S4
Canada

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
327
Abstract Views
1,659
Rank
148,946
PlumX Metrics