{"type":"ScholarlyArticle","title":"Improving Law Enforcement Daily Deployment Through Machine Learning-Informed Optimization under Uncertainty","authors":[{"name":"Jonathan Chase","slug":"jonathan-chase","given":"Jonathan","family":"Chase","affiliation":"Singapore Management University"},{"name":"Duc Thien Nguyen","slug":"duc-thien-nguyen","given":"Duc Thien","family":"Nguyen","affiliation":"Singapore Management University"},{"name":"Haiyang Sun","slug":"haiyang-sun","given":"Haiyang","family":"Sun","affiliation":"Singapore Management University"},{"name":"Hoong Chuin Lau","slug":"hoong-chuin-lau","given":"Hoong Chuin","family":"Lau","affiliation":"Singapore Management University"}],"abstract":"Urban law enforcement agencies are under great pressure to respond to emergency incidents effectively while operating within restricted budgets. Minutes saved on emergency response times can save lives and catch criminals, and a responsive police force can deter crime and bring peace of mind to citizens. To efficiently minimize the response times of a law enforcement agency operating in a dense urban environment with limited manpower, we consider in this paper the problem of optimizing the spatial and temporal deployment of law enforcement agents to predefined patrol regions in a real-world scenario informed by machine learning. To this end, we develop a mixed integer linear optimization formulation (MIP) to minimize the risk of failing response time targets. Given the stochasticity of the environment in terms of incident numbers, location, timing, and duration, we use Sample Average Approximation (SAA) to find a robust deployment plan. To overcome the sparsity of real data, samples are provided by an incident generator that learns the spatio-temporal distribution and demand parameters of incidents from a real world historical dataset and generates sets of training incidents accordingly. To improve runtime performance across multiple samples, we implement a heuristic based on Iterated Local Search (ILS), as the solution is intended to create deployment plans quickly on a daily basis. Experimental results demonstrate that ILS performs well against the integer model while offering substantial gains in execution time.","doi":"10.24963/ijcai.2019/806","url":"https://ijcai.org/proceedings/2019/806","pdf":"https://ijcai.org/proceedings/2019/0806.pdf","markdown":"https://ijcai.org/proceedings/2019/806.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/806","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"AI for Improving Human Well-being","track":"AI for Improving Human Well-being","number":806,"pages":{"first":5815,"last":5821},"keywords":["Special Track on AI for Improving Human-Well Being: AI benefits to society AI applications (Special Track on AI and Human Wellbeing)","Special Track on AI for Improving Human-Well Being: Societal applications (Special Track on AI and Human Wellbeing)"],"videos":[],"references":[{"position":1,"raw":"[Amador et al., 2014] Sofia Amador, Steven Okamoto, and Roie Zivan. Dynamic multi-agent task allocation with spatial and temporal constraints. In Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, AAMAS '14, pages 1495-1496, Richland, SC, 2014. International Foundation for Au- tonomous Agents and Multiagent Systems.","title":"Dynamic multi-agent task allocation with spatial and temporal constraints","authors":"Amador","year":"2014","venue":"Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, AAMAS '14","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Caplan et al., 2011] Joel M. Caplan, Leslie W. Kennedy, and Joel Miller. Risk terrain modeling: Brokering crim- inological theory and gis methods for crime forecasting. Justice Quarterly, 28(2):360-381, 2011.","title":"Risk terrain modeling: Brokering criminological theory and gis methods for crime forecasting","authors":"Joel M Caplan, Leslie W Kennedy, Joel Miller","year":"2011","venue":"Justice Quarterly","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chase et al., 2017] Jonathan Chase, Jiali Du, Na Fu, Truc Viet Le, and Hoong Chuin Lau. Law enforcement resource optimization with response time guarantees. In IEEE Symposium Series on Computational Intelligence (SSCI) 2017, 2017.","title":"Law enforcement resource optimization with response time guarantees","authors":"Jonathan Chase, Jiali Du, Na Fu, Truc Viet Le, Hoong Chuin Lau","year":"2017","venue":"IEEE Symposium Series on Computational Intelligence (SSCI) 2017","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Duvenaud et al., 2011] David K. Duvenaud, Hannes Nick- isch, and Carl E. Rasmussen. Additive Gaussian pro- cesses. In Proceedings of the Advances in Neural Infor- mation Processing Systems, pages 226-234, 2011.","title":"Additive Gaussian processes","authors":"David K Duvenaud, Hannes Nickisch, Carl E Rasmussen","year":"2011","venue":"Proceedings of the Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Flaxman et al., 2015] Seth Flaxman, Andrew Gordon Wil- son, Daniel B. Neill, Hannes Nickisch, and Alexander J. Smola. Fast Kronecker inference in Gaussian processes with non-Gaussian likelihoods. In Proceedings of the ICML, pages 607-616, 2015.","title":"Fast Kronecker inference in Gaussian processes with non-Gaussian likelihoods","authors":"Seth Flaxman, Andrew Gordon Wilson, Daniel B Neill, Hannes Nickisch, Alexander J Smola","year":"2015","venue":"Proceedings of the ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kennedy et al., 2011] Leslie W. Kennedy, Joel M. Caplan, and Eric Piza. Risk clusters, hotspots, and spatial intelli- gence: Risk terrain modeling as an algorithm for police re- source allocation strategies. Journal of Quantitative Crim- inology, 27(3):339-362, Sep 2011.","title":"Risk clusters, hotspots, and spatial intelligence: Risk terrain modeling as an algorithm for police resource allocation strategies","authors":"Leslie W Kennedy, Joel M Caplan, Eric Piza","year":"2011","venue":"Journal of Quantitative Criminology","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Lau et al., 2016] Hoong Chuin Lau, Zhi Yuan, and Aldy Gunawan. Patrol scheduling in urban rail network. An- nals of Operations Research, 239(1):317-342, 2016.","title":"Patrol scheduling in urban rail network","authors":"Zhi Hoong Chuin Lau, Aldy Yuan, Gunawan","year":"2016","venue":"Annals of Operations Research","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Levine, 2017] Ned Levine. CrimeStat: A Spatial Statistical Program for the Analysis of Crime Incidents, pages 381- 388. Springer International Publishing, Cham, 2017.","title":"CrimeStat: A Spatial Statistical Program for the Analysis of Crime Incidents","authors":"Ned Levine, Levine","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lourenc ¸o et al., 2010] Helena R Lourenc ¸o, Olivier C Mar- tin, and Thomas Stützle. Iterated local search: Framework and applications. Handbook of Metaheuristics, 246:363- 397, 2010.","title":"Iterated local search: Framework and applications","authors":"Helena R Lourenc ¸o, Thomas Olivier C Martin, Stützle","year":"2010","venue":"Handbook of Metaheuristics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Malleson and Andresen, 2015] Nick Malleson and Mar- tin A Andresen. Spatio-temporal crime hotspots and the ambient population. Crime Science, 4(1):1-8, 2015.","title":"Nick Malleson and Martin A Andresen. Spatio-temporal crime hotspots and the ambient population","authors":"Andresen Malleson","year":"2015","venue":"Crime Science","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Mukhopadhyay et al., 2016] Ayan Mukhopadhyay, Chao Zhang, Yevgeniy Vorobeychik, Milind Tambe, Kenneth Pence, and Paul Speer. Optimal allocation of police patrol resources using a continuous-time crime model. In De- cision and Game Theory for Security -7th International Conference, GameSec 2016, pages 139-158, 2016.","title":"Optimal allocation of police patrol resources using a continuous-time crime model","authors":"Ayan Mukhopadhyay, Chao Zhang, Yevgeniy Vorobeychik, Milind Tambe, Kenneth Pence, Paul Speer","year":"2016","venue":"Decision and Game Theory for Security -7th International Conference","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Murray et al., 2001] Alan T. Murray, Ingrid McGuffog, John S. Western, and Patrick Mullins. Exploratory spatial data analysis techniques for examining urban crimeimpli- cations for evaluating treatment. The British Journal of Criminology, 41(2):309-329, 2001.","title":"Exploratory spatial data analysis techniques for examining urban crimeimplications for evaluating treatment","authors":"Alan T Murray, Ingrid Mcguffog, John S Western, Patrick Mullins","year":"2001","venue":"The British Journal of Criminology","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Saisubramanian et al., 2015] Sandhya Saisubramanian, Pradeep Varakantham, and Hoong Chuin Lau. Risk based optimization for improving emergency medical systems. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI'15, pages 702-708. AAAI Press, 2015.","title":"Risk based optimization for improving emergency medical systems","authors":"Sandhya Saisubramanian, Pradeep Varakantham, Hoong Chuin Lau","year":"2015","venue":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI'15","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Wilson and Weiss, 2012] Jeremy M Wilson and Alexander Weiss. A performance-based approach to police staffing and allocation. US Department of Justice Office of Com- munity Oriented Policing Services, 2012.","title":"A performance-based approach to police staffing and allocation","authors":"M Jeremy, Alexander Wilson, Weiss","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}