No abstract

The proliferation of mobile devices and the emergence of the Internet of Things are leading to an unprecedented availability of operational data. In this article, we study how leveraging this data in conjunction with data science methods can help researchers and practitioners in the development and evaluation of new operational policies. Specifically, we introduce a two‐stage framework for exploratory data science consisting of a policy identification stage and an ex‐ante policy assessment stage. We apply the framework to the context of free‐floating carsharing—a novel mobility service that is an example of data‐rich smart city services. Through data exploration, we identify a novel preventive user‐based relocation policy and provide an ex‐ante assessment regarding the feasibility of its implementation. We discuss practical implications of our approach and results for shared‐mobility providers as well as the relationship between data science and operations management research.

Problem definition: We consider the case of prescriptive policing, that is, the data-driven assignment of police cars to different areas of a city. We analyze key problems with respect to prediction, optimization, and evaluation as well as trade-offs between different quality measures and crime types. Academic/practical relevance: Data-driven prescriptive analytics is gaining substantial attention in operations management research, and effective policing is at the core of the operations of almost every city in the world. Given the vast amounts of data increasingly collected within smart city initiatives and the growing safety challenges faced by urban centers worldwide, our work provides novel insights on the development and evaluation of prescriptive analytics applications in an urban context. Methodology: We conduct a computational study using crime and auxiliary data on the city of San Francisco. We analyze both strong and weak prediction methods along with two optimization formulations representing the deterrence and response time impact of police vehicle allocations. We analyze trade-offs between these effects and between different crime types. Results: We find that even weaker prediction methods can produce Pareto-efficient outcomes with respect to deterrence and response time. We identify three different archetypes of combinations of prediction methods and optimization objectives that constitute the Pareto frontier among the configurations we analyze. Furthermore, optimizing for multiple crime types biases allocations in a way that generally decreases single-type performance along one outcome metric but can improve it along the other. Managerial implications: Although optimization integrating all relevant crime types is theoretically possible, it is practically challenging because each crime type requires a collectively consistent weight. We present a framework combining prediction and optimization for a subset of key crime types with exploring the impact on the remaining types to support implementation of operations-focused smart city solutions in practice.