Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.

Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.

Author ORCID Identifier



Open Access Dissertation

Document Type


Degree Name

Doctor of Philosophy (PhD)

Degree Program


Year Degree Awarded


Month Degree Awarded


First Advisor

Ahmed Ghoniem

Subject Categories

Business Administration, Management, and Operations | Management Sciences and Quantitative Methods | Operational Research


Central to modern-time, consumer-focused retailing is the ability to provide attractive and reasonably-priced product assortments for different customer profiles. To this end, retailers can benefit from the use of data analytics in order to identify distinct customer segments, each characterized by their buying power, shopping behavior, and preferences. Further, retailers can also benefit from a careful examination of alternative procurement options and cost levers associated with products that are considered for inclusion in the assortment. Issues of assortment planning lie at the interface of operations and marketing. Profitable planning trade-offs can be identified using an optimization methodology and are simultaneously driven by consumer preferences and supply cost considerations. This dissertation proposes and investigates novel, integrated optimization models for assortment planning with the following overarching objectives: (i) To reveal insights into assortment decisions under product substitutability or complementarity and multiple customer segments; (ii) to improve the computational tractability of (nonlinear discrete) optimization models that arise in such contexts and to demonstrate their efficacy for large-scale data instances. In the first essay, we investigate the joint optimization of assortment and pricing decisions for complementary retail categories with relatively popular products having high and stable sales volumes, such as fast-moving consumer goods. Each category comprises substitutable items (e.g., different coffee brands) and the categories are related by cross-selling considerations that are empirically observed in marketing studies to be asymmetric in nature. That is, a subset of customers who purchase a product from a primary category (e.g., coffee) can typically opt to also buy from one or several complementary categories (e.g., sugar and/or coffee creamer). We propose a mixed-integer nonlinear program that maximizes the retailer's profit by jointly optimizing assortment and pricing decisions for multiple categories using a deterministic maximum-surplus consumer choice model. A linear mixed-integer reformulation is developed, which effectively enables an exact solution to large, industry-sized problem instances using commercial optimization solvers. Our computational study indicates that overlooking cross-selling between retail categories can result in substantial profit losses, suboptimal (narrower) assortments, and inadequate prices. The demonstrated tractability of the proposed model paves the way for "store-wide" optimization of categories that exhibit significant complementarity, which retailers can infer from market basket analysis. The second essay addresses an assortment packing problem where a decision maker optimizes the assortment and release times of products that belong to different categories over a multi-period planning horizon. Products in a same category are substitutable, whereas products across categories may exhibit complementarity relationships. All products have a longevity over which their attractiveness gradually decays (e.g., electronics or fashion products), while being positively or negatively impacted by the specific mix of substitutable or complementary products that the retailer has introduced. Our proposed 0-1 fractional program employs an attraction demand model and subsumes recent assortment packing models in the literature. We highlight the effect of overlooking cross-selling and cannibalization on the profit using an illustrative example. We develop linearized reformulation that afford exact solutions to small-sized problem instances. Furthermore, a linear programming-based heuristic approach is devised and is demonstrated to yield near-optimal solutions for large-scale computationally challenging problem instances in manageable times. Model extensions are discussed, especially in the context of the movie industry where exhibitors have to decide on the assortment of movies to display and their optimal display times.