报告题目：Proactive Policing: A Resource Allocation Model for Crime Prevention with Deterrence Effect

报 告 人：赵越

报告时间：2023年5月15日（星期一），10:00-11:30

报告地点：明哲楼326（腾讯会议同步直播，会议ID：363-323-915）

主办单位：东北财经大学现代供应链管理研究院

【报告人简介】

赵越博士目前就职于新加坡国立大学运筹中心，本科毕业于南京大学数学系，博士毕业于新加坡国立大学。他的研究兴趣主要有：（1）鲁棒机器学习、可信任机器学习（2）数据驱动的优化模型和鲁棒优化，以及其在交通管理、智慧城市、收益管理等领域的应用。他的研究成果已在人工智能和管理学的顶级期刊和会议上发表，如CVPR、TRB、IJOC等。

【摘要】

This paper addresses the issue of police resource allocation across multiple locations with the objective of minimizing the overall cost of potential crimes. In contrast to previous literature that concentrates on reactive police tasks such as shortening police response times, we present a proactive approach that emphasizes crime prevention from deterrence. To account for the deterrence effect of police resources on crime, we adopt the multinomial logit model to calibrate the distribution of crime locations. Our model sheds light on the two facets of the deterrence effect in proactive policing---the diffusion of crime control and the displacement of crimes---in criminology and economics related to modern crime patterns.  We also investigate the structural properties of our problem and its relationship to mixture-of-logits assortment optimization. Furthermore, we provide reformulations for mixed-integer linear/conic programs that can be solved directly by conventional optimization software. Finally, we showcase the efficacy of our model by presenting a data-driven case study on the allocation of surveillance cameras in New York City.

获取更多信息，请扫描下方二维码加入微信群，本群会作为长期供应链管理与科学领域学术交流群，直播结束后可在群内进行交流讨论。本群也会不定时分享相关学术资源及高水平学术讲座链接，欢迎各位老师同学加入微信群一起探讨学术问题。可同时登录现代供应链管理研究院网站：http://isca.dufe.edu.cn/，获取有关研究院的更多信息。