[Show abstract][Hide abstract] ABSTRACT: How to optimally configure its service resources is always a key for the service providers to improve efficiency and quality of service. Fail to optimize service capability often causes long queues in many on-site service outlets, for example, retail stores, bank branches or government agencies. A first step to do service capability configuration is to identify and understand customer demand and preference. In previous research, these metrics are often obtained by general high-level (e.g. city level or district level) surveys which are not detailed enough for modeling specific customer experience at a given site. Further more, customer satisfaction is not considered as a key objective compared to cost and profit, which often leads to decisions that do not accommodate customer experiences adequately. A deep understanding of customer behavior will greatly help service providers achieve the commercial transformation from product-centric to customer-centric and enhance their market share and competitive strength. In this paper, we propose a customer-centric service resource reconfiguration method which identifies customer demand and preference from internal historical transaction data. Agent simulation is adopted to model the stochastic service processes and customer behavior in optimizing service resources.
[Show abstract][Hide abstract] ABSTRACT: It is critical for retail enterprises to select good sites or locations to open their stores, especially in current competitive retail market. However, evaluating the goodness of sites in real business applications is a complex problem. That is, how to judge whether the market around a store site is good? We don't know the exact mechanism of how a site can be good and it is hard to have correct site goodness values as supervised labels. The Retail Outlet Site Evaluation (ROSE) tool is designed to learn the site evaluation model by integrating city geographic & demographic data and two kinds of expert knowledge: sample preference and feature preference. The feature preference information can help greatly reduce the required number of sample preferences. It enables our application practicable because it is almost impossible to give such amount of sample preference pairs manually by experts when ranking hundreds of data points. In the experiment and case study part, we show that the ROSE tool can achieve good results and useful for users to do site evaluation work in real cases.
[Show abstract][Hide abstract] ABSTRACT: Solving the problem of long queues becomes increasingly urgent in many on-site service outlets. For example, in a bank branch or a government agency, customers may have to wait for a very long time to be served. How to optimally reconfigure the capability of service channels in such outlets is a key for the service providers to improve efficiency and quality of service. In this paper, we propose a method to optimally configure service channels at a given service outlet. We integrate customer experience metrics with cost and profit into a unified objective function for optimization. Multi-agent simulation technique is employed to model the stochastic service processes and customer behavior, and to evaluate the objective function in optimizing service channel capacity. Some real-life data collected from bank branches provide significant empirical support to the method and demonstrate that the presented method is both effective and efficient.