Dorothee Honhon

Demand seasonality in retail inventory management

We investigate the value of accounting for demand seasonality in inventory control. Our problem is motivated by discussions with retailers who admitted to not taking perceived seasonality patterns into account in their replenishment systems. We consider a single-location, single-item periodic review lost sales inventory problem with seasonal demand in a retail environment. Customer demand has seasonality with a known season length, the lead time is shorter than the review period and orders are placed as multiples of a fixed batch size. The cost structure comprises of a fixed cost per order, a cost per batch, and a unit variable cost to model retail handling costs. We consider four different settings which differ in the degree of demand seasonality that is incorporated in the model: with or without within-review period variations and with or without across-review periods variations. In each case, we calculate the policy which minimizes the long-run average cost and compute the optimality gaps of the policies which ignore part or all demand seasonality. We find that not accounting for demand seasonality can lead to substantial optimality gaps, yet incorporating only some form of demand seasonality does not always lead to cost savings. We apply the problem to a real life setting, using Point-of-Sales data from a European retailer. We show that a simple distinction between weekday and weekend sales can lead to major cost reductions without greatly increasing the complexity of the retailer’s automatic store ordering system. Our analysis provides valuable insights on the tradeoff between the complexity of the automatic store ordering system and the benefits of incorporating demand seasonality.

Flexibility and Reputation in Repeated Prisoners' Dilemma Games

We study the role that the option to terminate a relationship has on cooperation in a repeated prisoners dilemma. While cooperation is, in theory, sustainable with or without this option, we show experimentally that cooperation rates are significantly lower with the option to terminate. Rather than punishing a defection, most subjects choose to terminate the relationship, which increases the temptation to behave opportunistically. However, we show that introducing a reputation mechanism, through which signals of past cooperative behavior are given to future matches, can substantially increase cooperation rates, in some cases to a level higher than when the option to terminate the relationship is absent. Our results show that an objective, long-lasting measure of reputation is the most effective in promoting cooperation, but short-lasting or subjective but long-lasting reputation mechanisms also increase cooperative behavior. Moreover, reputation mechanisms generally lead to stable cooperation rates over time, in contrast to the declining cooperation rates observed in their absence when subjects are free to terminate relationships. Finally we show that the option to terminate a relationship acts as a sorting mechanism between subjects who cooperate frequently and those who do not, and that reputation mechanisms further enhance this sorting effect.

Positioning and Pricing of Horizontally Differentiated Products

We provide structural results and a solution method for designing horizontally differentiated product lines – optimizing product positions and prices – under fairly general consumer choice behavior. Our choice model is a generalization of the basic Hotelling-Lancaster locational choice model: Consumer tastes (ideal products) follow a general distribution; substitution disutility (transportation cost) can be an asymmetric convex function of product-spatial distance; and the market may not be fully covered. We formalize the notion that a shift of consumer tastes toward one end of the product space cannot result in a shift of the optimal product line in the opposite direction. For a unimodal taste distribution, we show that with respect to the product that covers the mode (or one of two products adjacent to it) prices and market shares drop toward the tails. Hence, higher popularity is always associated with higher price – although pricing, positioning, relative market share and popularity of products are all endogenous in our model. Our solution method is exact for discrete consumer taste distributions. Whereas, for continuous distributions, it requires lower and upper bounds, which can be computed efficiently using shortest path formulations and they asymptotically converge to the optimal profit.

A Shortest-Path Algorithm for the Departure Time and Speed Optimization Problem

We present a shortest-path algorithm for the departure time and speed optimization problem under traffic congestion. The objective of the problem is to determine an optimal schedule for a vehicle v...

Understanding the Behavioral Drivers of Execution Failures in Retail Supply Chains: An Experimental Study Using Virtual Reality

We conduct a real-effort experiment in an immersive virtual environment and quantify the impact of product similarity on operational execution in a retail setting. In our experiments, subjects must identify and sort two types of products based on their observable characteristics. We find measures of operational execution to be substantially lower when the observable characteristics of the two products types are very similar compared to when they are dissimilar. Specifically, we observe more sorting errors and more products left unsorted when subjects handle products with more similar observable characteristics. Introducing a visual cue to distinguish products improves execution when the products are dissimilar (by lowering the frequency of sorting mistakes) and, even more so, when they are similar (by reducing both the number of sorting mistakes and the number of products left unsorted). Overall performance (measured by the faction of products correctly sorted) increases by approximately 22 percent, on average, when subjects handle products with observable characteristics that are easier to distinguish. Using three-dimensional real-time movement measurements of our subjects, we discuss differences among high- and low-performing subjects as well as the managerial implications of our findings for product design, packaging, and labeling on execution performance in the retail context.