Operations & Supply Chain Management

We propose a method for estimating substitute and lost demand when only sales and product availability data are observable, not all products are displayed in all periods (e.g., due to stock-outs or availability controls), and the seller knows its aggregate market share. The model combines a multinomial logit (MNL) choice model with a non-homogeneous Poisson model of arrivals over multiple periods. Our key idea is to view the problem in terms of primary (or first-choice) demand; that is, the demand that would have been observed if all products had been available in all periods.

Nursing care is arguably the single biggest factor in both the cost of hospital care and patient satisfaction. Inadequate inpatient nursing levels have also been cited as a significant factor in medical errors and emergency room overcrowding. Yet, there is widespread dissatisfaction with the current methods of determining nurse staffing levels, including the most common one of using minimum nurse-to-patient ratios. In this paper, we represent the nursing system as a variable finite-source queuing model.

Customer switching costs are an important factor in account-based services such as telecommunications, financial, insurance and brokerage services. In these businesses, existing customers incur significant costs if they switch to another provider. Such costs include physical configuration and installation costs, contractual costs (e.g. termination fees) and cognitive costs of learning. These switching costs enable a firm to extract more revenue from incumbent customers by charging them higher prices.

Scarcity has long been known to impact consumers' choices. Yet, the impact of shelf-based scarcity in retail environments, created by stocking level depletion, has received almost no attention in the literature. Indeed, little research to date has even examined if consumers will attend to shelf-based scarcity in retail environments, much less how this cue can impact choice. A priori, given the inherently noisy and cue-filled nature of retail environments, it is quite reasonable to expect that shelf-based scarcity would play little to no role in consumers' choices.

The principal performance measures in an inventory system involve key characteristics of the system's inventory position, i.e., the total inventory the firm is economically committed to, as well as the average order size or order frequency. As to the former, the focus among operation managers is on the maximum inventory (position), the average inventory and the minimum inventory, the latter being related to the so-called safety stock concept. Financial analysts and macroeconomists pay particular attention to the sales/inventory ratio, also referred to as the inventory turnover.

Capacity decisions in service operations often involve a trade-off between operating cost and the level of service offered to customers. Although the cost of attaining a pre-specified level of service has been well-studied, there isn't much research studying how customer service levels affect revenue and profit. This paper conducts an empirical study to analyze how waiting in a queue in the context of a retail store affects customer purchasing behavior. Our methodology uses a novel technology based on digital imaging to record periodic information about the queuing system.

We address the following problems that arise in the management of call center operating under certain Service Level Agreements (SLAs): (1) setting the capacity levels of the agent pools; (2) constructing a routing scheme for arriving customers; and (3) devising a dynamic priority rule for customers waiting at each pool. We develop a mathematical programming approach to simultaneously solve this integrated planning problem and show how it can be used in strategic call center design studies.

We consider a sequential adaptive allocation problem which is formulated as a traditional two armed bandit problem but with one important modification: at each time step t, before selecting which arm to pull, the decision maker has access to a random variable Xt which provides information on the reward in each arm. Performance is measured as the fraction of time an inferior arm (generating lower mean reward) is pulled.

Maximizing throughput for heterogeneous parallel server queues has received quite a bit of attention from the research community and the stability region for such systems is well understood.  However, many real-world systems have periods where they are temporarily overloaded.  Under such scenarios, the unstable queues often starve limited resources.  This work examines what happens during periods of temporary overload.  Specifically, we look at how to fairly distribute stress.  We explore the dynamics of the queue workloads under the MaxWeight scheduling policy duri