skip to main content


Title: Data-Driven Optimization for Atlanta Police-Zone Design
We present a data-driven optimization framework for redesigning police patrol zones in an urban environment. The objectives are to rebalance police workload along geographical areas and to reduce response time to emergency calls. We develop a stochastic model for police emergency response by integrating multiple data sources, including police incident reports, demographic surveys, and traffic data. Using this stochastic model, we optimize zone-redesign plans using mixed-integer linear programming. Our proposed design was implemented by the Atlanta Police Department in March 2019. By analyzing data before and after the zone redesign, we show that the new design has reduced the response time to high-priority 911 calls by 5.8% and the imbalance of police workload among Atlanta’s zones by 43%.  more » « less
Award ID(s):
2015787
NSF-PAR ID:
10385656
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
INFORMS Journal on Applied Analytics
Volume:
52
Issue:
5
ISSN:
2644-0865
Page Range / eLocation ID:
412 to 432
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    The murder of George Floyd triggered a broad social response and noticeable shift in public opinion of policing. Since policing is dependent upon public cooperation, a question is whether the shift in opinion had an effect on police calls-for-service. Data from Los Angeles and New York City are evaluated using a regression discontinuity design. Violent crime, property crime, and quality-of-life disorder calls are analyzed to address differences in reporting norms. The role of racial–ethnic composition of local areas is assessed by examining census tracts where the majority of the residential population is Asian, Black, Hispanic, or White. Following the murder of George Floyd, in New York City violent crime, property crime, and quality-of-life calls all increased significantly. In Los Angeles, quality-of-life calls for service decreased significantly. The increase in violent crime calls observed in New York was greatest in areas where the majority of residents are Black, whereas the increase in property crime calls was the greatest in areas where a majority of residents are White. The decrease in quality-of-life calls observed in Los Angeles was in areas where the majority of residents are White. In both cases, the effect was relatively short-lived.

     
    more » « less
  2. The problem of dispatching emergency responders to service traffic accidents, fire, distress calls and crimes plagues urban areas across the globe. While such problems have been extensively looked at, most approaches are offline. Such methodologies fail to capture the dynamically changing environments under which critical emergency response occurs, and therefore, fail to be implemented in practice. Any holistic approach towards creating a pipeline for effective emergency response must also look at other challenges that it subsumes - predicting when and where incidents happen and understanding the changing environmental dynamics. We describe a system that collectively deals with all these problems in an online manner, meaning that the models get updated with streaming data sources. We highlight why such an approach is crucial to the effectiveness of emergency response, and present an algorithmic framework that can compute promising actions for a given decision-theoretic model for responder dispatch. We argue that carefully crafted heuristic measures can balance the trade-off between computational time and the quality of solutions achieved and highlight why such an approach is more scalable and tractable than traditional approaches. We also present an online mechanism for incident prediction, as well as an approach based on recurrent neural networks for learning and predicting environmental features that affect responder dispatch. We compare our methodology with prior state-of-the-art and existing dispatch strategies in the field, which show that our approach results in a reduction in response time of responders with a drastic reduction in computational time. 
    more » « less
  3. The problem of dispatching emergency responders to service traffic accidents, fire, distress calls and crimes plagues urban areas across the globe. While such problems have been extensively looked at, most approaches are offline. Such methodologies fail to capture the dynamically changing environments under which critical emergency response occurs, and therefore, fail to be implemented in practice. Any holistic approach towards creating a pipeline for effective emergency response must also look at other challenges that it subsumes - predicting when and where incidents happen and understanding the changing environmental dynamics. We describe a system that collectively deals with all these problems in an online manner, meaning that the models get updated with streaming data sources. We highlight why such an approach is crucial to the effectiveness of emergency response, and present an algorithmic framework that can compute promising actions for a given decision-theoretic model for responder dispatch. We argue that carefully crafted heuristic measures can balance the trade-off between computational time and the quality of solutions achieved and highlight why such an approach is more scalable and tractable than traditional approaches. We also present an online mechanism for incident prediction, as well as an approach based on recurrent neural networks for learning and predicting environmental features that affect responder dispatch. We compare our methodology with prior state-of-the-art and existing dispatch strategies in the field, which show that our approach results in a reduction in response time with a drastic reduction in computational time. 
    more » « less
  4. null (Ed.)
    The broad adoption of fanout queries on distributed datastores has made asynchronous event-driven datastore drivers a natural choice due to reduced multithreading overhead. However, through extensive experiments using the latest datastore drivers (e.g., MongoDB, HBase, DynamoDB) and YCSB benchmark, we show that an asynchronous datastore driver can cause unexpected performance degradation, especially in fanout-query scenarios. For example, the default MongoDB asynchronous driver adopts the latest Java asynchronous I/O library, which uses a hidden on-demand JVM level thread pool to process fanout query responses, causing a surprising multithreading overhead when the query response size is large. A second instance is the traditional wisdom of modular design of an application server and the embedded asynchronous datastore driver can cause an imbalanced workload between the two components due to lack of coordination, incurring frequent unnecessary system calls. To address the revealed problems, we introduce DoubleFaceAD--a new asynchronous datastore driver architecture that integrates the management of both upstream and downstream workload traffic through a few shared reactor threads, with fanout-query-aware priority-based scheduling to reduce the overall query waiting time. Our experimental results on two representative application scenarios (YCSB and DBLP) show DoubleFaceAD outperforms all other types of datastore drivers up to 34% on throughput and 1.9\texttimes{} faster on 99th percentile response time. 
    more » « less
  5. This research evaluates the impact of switching college engineering courses from in-person instruction to emergency remote learning among engineering students at a university in the Midwest. The study aimed to answer the question: What were the concerns and perceived challenges students faced when traditional in-person engineering courses suddenly transitioned to remote learning? The goal of this study is to uncover the challenges students were facing in engineering online courses and to understand students’ concerns. Our findings can help improve teaching instruction to provide students with previously unavailable educational assistance for online engineering courses. We collected online survey responses during weeks 8 and 9 of the academic semester, shortly after the COVID-19 shutdown and emergency transition to remote learning in Spring 2020. The survey included two open-ended questions which inquired about students’ feedback about moving the class online, and one two-item scale which assessed students’ confidence in online engineering learning. Data analysis for the open-ended questions was guided by the theoretical framework - Social Cognitive Career Theory [1] that explores how context, person factors and social cognitions contribute to career goals, interests and actions. A phenomenological approach [2] was conducted to understand the experience of these students. Open coding and axial coding [2] methods were used to create initial categories then themes related to students' concerns and challenges. Data from the two-item scale was evaluated using descriptive statistics: means, standard deviations, and ranges. Four main themes with separate sub-categories emerged from the student responses: 1) Instructor’s ability to teach course online (Instructional limitations, Seeking help, Increased Workload), 2) Student’s ability to learn online (Time Management, Lower engagement and motivation, Harder to absorb material, Hard to focus, Worry about performance), 3) Difficulties outside of class (Technology issues), and 4) No concerns. Students seemed more concerned about their ability to learn the material (48% of responses) than the instructor’s ability to teach the material (36% of responses). The instructional limitations or lack of instructional support (22% of responses) and time management (12% of responses) were among the major concerns in the sub-categories. The results from two-item scale indicated participants' s confidence in their ability to master their classroom knowledge was at an intermediate level via online instruction (6/10), and participants' confidence in the instructor's ability to teach knowledge in online classes is moderate to high (7/10). The results align with the open-ended question response in which students were somewhat more concerned about their ability to learn than the instructor’s ability to teach. The themes and analysis will be a valuable tool to help institutions and instructors improve student learning experiences. 
    more » « less