Back to search

Georgia Institute of Technology

Analytics for Sustainable and Retail Operations

Abstract

dc:description.abstract

This dissertation focuses on two applications of analytics in sustainable and retail operations. In chapter 2, we design a priority-based inspection strategy for the Environmental Protection Agency (EPA) Region 2. Government regulators such as the U.S. EPA are obligated to inspect facilities regularly to ensure compliance with environmental laws and requirements. Faced with limited budget and resources, regulators can only inspect a small fraction of facilities within a specific time frame. We propose a new inspection strategy that can help environmental regulators prioritize facilities to be inspected under a limited budget. We formulate the problem as a restless multiarmed bandit model and develop an index-based inspection policy. We also demonstrate how to extend the model to incorporate heterogeneous inspection costs and the possibility of environmental disaster. Simulations using data from EPA Region 2 indicate the benefits of our proposed index-based compliance monitoring strategy over other benchmark policies used in academic literature and practice in reducing the harm to the environment and public health. In chapter 3, we partner with a consumer electronics retailer, and show how incorporating substitution and competition effects, two integral components of today's competitive markets, enhance the accuracy of the demand prediction models. The complicated relationship between the demand of the focal product and the substitutes' prices makes linear models incapable of estimating the cross-price elasticities. We suggest a structure-imposed neural network and demonstrate how it can be utilized in multiproduct pricing decision tools. Our imposed structure mitigates the practical concerns around the interpretability of the neural networks, which has hindered their adoption in revenue management.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Industrial and Systems Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2020

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Mohammad Shahi, Yasaman
Advisors dc:contributor.advisor
  • Toktay, L. Beril
  • Keskinocak, Pinar
  • Wang, He
Committee members dc:contributor.committeemember
  • Goldsman, David
  • Ferreira, Kris

Subjects

dc:subject × 2

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/65008

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Mohammad Shahi, Yasaman. Analytics for Sustainable and Retail Operations. Doctoral thesis, Georgia Institute of Technology, 2020. http://hdl.handle.net/1853/65008