Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
John Bertetto

    John Bertetto

    Law enforment strategists must understand the complex network of relationships in their operational environment and use this knowledge to design adap-tive strategies that target those relationships. In doing so, law enforcement agencies... more
    Law enforment strategists must understand the complex network of relationships in their operational environment and use this knowledge to design adap-tive strategies that target those relationships. In doing so, law enforcement agencies may find themselves with a thorough enough understanding of the various criminal organizations within their operational environment that they can anticipate likely responses to enforcement actions and plan the next wave of enforcement actions in advance.
    By understanding the environment as it exists in real time and continuing the cycle of understanding, designing, influencing, and evaluating, designers can guide their target through a series of intended responses. When used against
    criminal organizations, such as street gangs, adaptive strategies target and exploit the relationships among middle-tier operators resulting in their incarceration and removal from the operational environment. Without these middle-tier operators, the ability for the criminal
    organization to effectively conduct its criminal affairs is lost, resulting in the disruption, destabilization, and dismantling of the organization in a way that prevents a power vacuum and the violence typically associated with it.
    Research Interests:
    As law enforcement professionals, we often hold two things as fact. First, we acknowledge that the world in which we operate is ever changing and different than the one we were familiar with in the past. Second, when designing strategies... more
    As law enforcement professionals, we often hold two things as fact. First, we acknowledge that the world in which we operate is ever changing and different than the one we were familiar with in the past. Second, when designing strategies to combat crime and criminal activity, we look into the past for strategies that have proven successful and reimplement them. That the contradictory nature of these two things is rarely recognized and even more rarely reconciled continues to be a source of mystery. However, by placing these two statements side by side, it should be clear that they stand in direct conflict with one another. If today’s operational environment is different than that of the past, how can any previously implemented strategy have any real hope of being successful? Crime and criminal organizations may be similar to those that came before them, but the players and their relationships with each other are different. This dramatically affects our existing framework for underst...
    Elham Shaabani, Ashkan Aleali, Paulo Shakarian, John Bertetto  KDD 2015 (Aug., 2015)  Gang violence is a major problem in the United States ac-  counting for a large fraction of homicides and other vio-  lent crime. In this paper, we... more
    Elham Shaabani, Ashkan Aleali, Paulo Shakarian, John Bertetto 

    KDD 2015 (Aug., 2015) 

    Gang violence is a major problem in the United States ac- 
    counting for a large fraction of homicides and other vio- 
    lent crime. In this paper, we study the problem of early 
    identification of violent gang members. Our approach re- 
    lies on modified centrality measures that take into account 
    additional data of the individuals in the social network of 
    co-arrestees which together with other arrest metadata pro- 
    vide a rich set of features for a classification algorithm. We 
    show our approach obtains high precision and recall (0.89 
    and 0.78 respectively) in the case where the entire network 
    is known and out-performs current approaches used by law- 
    enforcement to the problem in the case where the network 
    is discovered overtime by virtue of new arrests - mimick- 
    ing real-world law-enforcement operations. Operational is- 
    sues are also discussed as we are preparing to leverage this 
    method in an operational environment
    Research Interests:
    In this paper, we study a variant of the social network maximum influence problem and its application to intelligently approaching individual gang members with incentives to leave a gang. The goal is to identify individuals who when... more
    In this paper, we study a variant of the social network
    maximum influence problem and its application to intelligently
    approaching individual gang members with incentives
    to leave a gang. The goal is to identify individuals who
    when influenced to leave gangs will propagate this action.
    We study this emerging application by exploring specific
    facets of the problem that must be addressed when modeling
    this particular situation. We formulate a new influence
    maximization variant - the “social incentive influence”
    (SII) problem and study it both formally and in the context
    of the law-enforcement domain. Using new techniques
    from unconstrained submodular maximization, we develop
    an approximation algorithm for SII and present a suite of
    experimental results - including tests on real-world police
    data from Chicago.