Sparse Flexible Design: A Machine Learning Approach

47 Pages Posted: 6 Jun 2019

See all articles by Timothy Chan

Timothy Chan

University of Toronto, Mechanical and Industrial Engineering Department

Daniel Letourneau

affiliation not provided to SSRN

Benjamin Potter

University of Toronto, Mechanical and Industrial Engineering Department

Date Written: May 17, 2019

Abstract

For a general production network, state-of-the-art methods for constructing sparse flexible designs are heuristic in nature, typically computing a proxy for the quality of unseen networks and using that estimate in a greedy manner to modify a current design. This paper develops two machine learning-based approaches to constructing sparse flexible designs that leverage a neural network to accurately and quickly predict the performance of large numbers of candidate designs. We demonstrate that our heuristics are competitive with existing approaches and produce high-quality solutions for both balanced and unbalanced networks. Finally, we introduce a novel application of process flexibility in healthcare operations to demonstrate the effectiveness of our approach in a large numerical case study. We study the flexibility of linear accelerators that deliver radiation to treat various types of cancer. We demonstrate how clinical constraints can be easily absorbed into the machine learning subroutine and how our sparse flexible treatment networks meet or beat the performance of those designed by state-of-the-art methods.

Keywords: process flexibility, sparse network design, machine learning, neural network, healthcare operations, radiation therapy, optimization, network flow

JEL Classification: C61,L60

Suggested Citation

Chan, Timothy and Letourneau, Daniel and Potter, Benjamin, Sparse Flexible Design: A Machine Learning Approach (May 17, 2019). Available at SSRN: https://ssrn.com/abstract=3390000 or http://dx.doi.org/10.2139/ssrn.3390000

Timothy Chan

University of Toronto, Mechanical and Industrial Engineering Department ( email )

Toronto
Canada

Daniel Letourneau

affiliation not provided to SSRN

Benjamin Potter (Contact Author)

University of Toronto, Mechanical and Industrial Engineering Department ( email )

Toronto
Canada

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

Paper statistics

Downloads
74
Abstract Views
566
rank
379,199
PlumX Metrics