Access Type

Open Access Dissertation

Date of Award

January 2018

Degree Type

Dissertation

Degree Name

Ph.D.

Department

Industrial and Manufacturing Engineering

First Advisor

Ratna B. Chinnam

Abstract

Growing competitiveness and increasing availability of data is generating tremendous interest in data-driven analytics across industries. In the retail sector, stores need targeted guidance to improve both the efficiency and effectiveness of individual stores based on their specific location, demographics, and environment. We propose an effective data-driven framework for internal benchmarking that can lead to targeted guidance for individual stores. In particular, we propose an objective method for segmenting stores using a model-based clustering technique that accounts for similarity in store performance dynamics. It relies on effective Finite Mixture of Regression (FMR) techniques for carrying out the model-based clustering with grouping structure (`must-link' constraints) and modeling store performance. We propose two alternate methods for FMR with grouping structure: 1) Competitive Learning (CL) and 2) Expectation Maximization (EM). The CL method can support both linear and non-linear regression methods whereas the more effective proposed EM approach only supports linear regression.

We also propose an optimization framework to derive tailored recommendations for individual stores within store clusters that jointly improves profitability for the store while also improving sales to satisfy franchiser requirements. We validate the methods using synthetic experiments as well as a real-world automotive dealership network study for a leading global automotive manufacturer.

Share

COinS