Determining visitor engagement through augmented reality at science festivals: An experience economy perspective

Service innovation is intertwined with service design, and knowledge from both fields should be integrated to advance theoretical and normative insights. However, studies bridging service innovatio...

Big Data, Big Insights? Advancing Service Innovation and Design With Machine Learning:

https://pure.rug.nl/ws/files/46874179/1_s2.0_S0148296317302394_main.pdf

The impact of positive and negative emotions on loyalty intentions and their interactions with customer equity drivers

The purpose of this paper is to present exciting and innovative research questions in service operations that are aligned with eight key themes and related topics determined by the Journal of Service Management (JOSM) Service Operations Expert Research Panel. By offering a good number of such research questions, this paper provides a broad range of ideas to spur conceptual and empirical research related to service operations and encourage the continued creation of deep knowledge within the field, as well as collaborative research across disciplines that develops and incorporates insights from service operations.,Based on a Delphi study, described in the companion article, “Service Operations: What Have We Learned?,” the panel identified eight key research themes in service operations where leading-edge research is being done or has yet to be done (Victorino et al., 2018). In this paper, three or four topics within each theme are selected and multiple questions for each topic are proposed to guide research efforts. The topics and questions, while wide-ranging, are only representative of the many ongoing research opportunities related to service operations.,The field of service operations has many interesting research topics and questions that are largely unexplored. Furthermore, these research areas are not only increasingly integrative across multiple themes within operations but often transcend functional disciplines. This creates opportunities for ever more impactful research with a greater reach throughout the service system and suggests that service researchers, regardless of functional affiliation, can contribute to the ongoing conversation on the role of service operations in value creation.,Leveraging the collective knowledge of the JOSM Service Operations Expert Research Panel to expand on the research themes generated from the Delphi study, novel questions for future study are put forward. Recognizing that the number of potential research questions is virtually unlimited, summary questions by theme and topic are also provided. These questions represent a synopsis of the individual questions and can serve as a quick reference guide for researchers interested in pursuing new directions in conceptual and empirical research in service operations. This summary also serves as a framework to facilitate the formulation of additional research topics and questions.

/pdf/service-operations-what-s-next-3ycnsro3mt.pdf

Service operations: what’s next?

The multiarmed bandit problem is a popular framework for studying the exploration versus exploitation trade-off. Recent applications include dynamic assortment design, Internet advertising, dynamic pricing, and the control of queues. The standard mathematical formulation for a bandit problem makes the strong assumption that the decision maker has a full characterization of the joint distribution of the rewards, and that “arms” under this distribution are independent. These assumptions are not satisfied in many applications, and the out-of-sample performance of policies that optimize a misspecified model can be poor. Motivated by these concerns, we formulate a robust bandit problem in which a decision maker accounts for distrust in the nominal model by solving a worst-case problem against an adversary (“nature”) who has the ability to alter the underlying reward distribution and does so to minimize the decision maker’s expected total profit. Structural properties of the optimal worst-case policy are charac...

Robust Multiarmed Bandit Problems

For many consumer-intensive (i.e., business-to-consumer) services, delivering memorable customer experiences is a source of competitive advantage. Yet there are few guidelines available for designing service encounters with a focus on customer satisfaction. In this paper, we show how experiential services should be sequenced and timed to maximize the satisfaction of customers who are subject to memory decay and acclimation. We find that memory decay favors positioning the highest service level near the end, whereas acclimation favors maximizing the gradient of service level. Together, they maximize the gradient of service level near the end. Although memory decay and acclimation lead to the same design individually, they can act as opposing forces when considered jointly. Overall, our analysis suggests that short experiences should have activities scheduled as a crescendo and duration allocated primarily to the activities with the highest service levels, whereas long experiences should have activities sch...

The Design of Experiential Services with Acclimation and Memory Decay: Optimal Sequence and Duration

We study a robust model of the multi-armed bandit (MAB) problem in which the transition probabilities are ambiguous and belong to subsets of the probability simplex. We first show that for each arm there exists a robust counterpart of the Gittins index that is the solution to a robust optimal stopping-time problem and can be computed effectively with an equivalent restart problem. We then characterize the optimal policy of the robust MAB as a project-by-project retirement policy but we show that arms become dependent so the policy based on the robust Gittins index is not optimal. For a project selection problem, we show that the robust Gittins index policy is near optimal but its implementation requires more computational effort than solving a non-robust MAB problem. Hence, we propose a Lagrangian index policy that requires the same computational effort as evaluating the indices of a non-robust MAB and is within 1 % of the optimum in the robust project selection problem.

/pdf/robust-control-of-the-multi-armed-bandit-problem-1hw8q2zb0g.pdf

Robust control of the multi-armed bandit problem

For many consumer-intensive (B2C) services, delivering memorable customer experiences to maximize customer satisfaction can be a source of competitive advantage. Yet, there is no clear guideline available for service encounter design that accounts for customer behavior. In this paper, we show how experiential services should be sequenced and timed to maximize satisfaction of customers who are subject to memory decay and acclimation. We find that memory decay favors positioning the highest service level near the end, whereas acclimation favors maximizing the gradient of service level. Although memory decay and acclimation lead to the same design individually, they can act as opposing forces when considered jointly. Specifically, together, they maximize the gradient of service level near the end, which may result in (i) sequencing activities in a U-shaped fashion and (ii) lengthening the duration of activities with the lowest service levels. Based on the analytical characterization of the optimal sequence and timing of activities, we propose heuristics to design the service encounter. Overall, this paper shows that service experiences can be engineered to enhance customer satisfaction.

We study a robust model of the multi-armed bandit (MAB) problem in which the transition probabilities are ambiguous and belong to subsets of the probability simplex. We characterize the optimal policy as a project-by-project retirement policy but we show that arms become dependent so the Gittins index is not optimal. We propose a Lagrangian index policy that is computationally equivalent to evaluating the indices of a non-robust MAB. For a project selection problem we fi nd that it performs near optimal.

/pdf/robust-control-of-the-multi-armed-bandit-problem-4jvetyre1g.pdf

Robust Control of the Multi-Armed Bandit Problem

In e-commerce, a group of similar or complementary products is recommended as a bundle based on the product category. Existing work on modeling bundle recommendations consists of graph-based approaches. In these methods, user-product interactions provide a more personalized experience. Moreover, these approaches require robust user-product interactions and cannot be applied to cold start scenarios. When a new product is launched or for products with limited purchase history, the lack of user-product interactions will render these algorithms inaccessible. Hence, no bundles recommendations will be provided to users for such product categories. These scenarios are frequent for retailers like Target, where much of the stock is seasonal, and new brands are launched throughout the year. This work alleviates this problem by modeling product bundles recommendation as a supervised graph link prediction problem. A graph neural network (GNN) based product bundles recommendation system, BundlesSEAL is presented. First, we build a graph using add-to-cart data and then use BundlesSEAL to predict the link representing bundles relation between products represented as nodes. We also propose a heuristic to identify relevant pairs of products for efficient inference. Further, we also apply BundlesSEAL for predicting the edge weights instead of just link existence. BundlesSEAL based link prediction leads to amelioration of the above-mentioned cold start problem by increasing the coverage of product bundles recommendations in various categories by 50% while achieving a 35% increase in revenue over behavioral baseline. The model was also validated over the Amazon product metadata dataset.

Aparupa Das Gupta

Papers

The Design of Experiential Services with Acclimation and Memory Decay: Optimal Sequence and Duration

Robust control of the multi-armed bandit problem

The Design of Experiential Services with Acclimation and Memory Decay: Optimal Sequence and Duration

Robust Control of the Multi-Armed Bandit Problem

Improving Bundles Recommendation Coverage in Sparse Product Graphs