I-Corps: Innovative Use of Internet Classifieds in Law Enforcement Investigations

该项目涉及在海量在线信息上使用机器学习技术，以确定在执法实践和公共政策中有用的模式。公共数据的数量和复杂性使寻求查明非法活动的调查部队手动浏览和跟踪是不切实际的。例如，有必要使人口贩运，特别是性贩运的情报模式的侦测过程自动化。互联网的无处不在为利用贩运受害者的犯罪者提供了在广告网站上索要服务的能力。这些数据是公开的，其中包含可能有助于执法调查人员了解犯罪模式和追踪肇事者的信息。该团队建议研究他们为该任务开发的原型分析工具的商业化机会。这项技术可以节省时间，提高执法效率和效率，因为它提供了原本可能会遗漏的新线索。该项目提供了一个框架，用于在具有重要社会意义的应用的重点背景下，展示以前由NSF资助的机器学习研究的实际效用。这项拟议的创新有可能彻底改变美国地方、州和联邦各级的调查程序。网上的海量数据目前没有得到充分利用。这个项目试图为了社会的普遍利益而纠正这一点。它将提高各级(地方、州、联邦)执法实践的效率，促进跨机构合作，并加强公共政策研究。拟议的创新还将在利用公共数据来源检测和绘制其他非法行为(例如销售被盗和假冒商品)和非非法行为(例如经济活动、找工作、生活方式和公共卫生)模式方面有更广泛的应用。

This project addresses the use of machine learning techniques on massive on-line information for identifying patterns useful in law enforcement practice and public policy. The quantity and complexity of public data make it impractical for manual browsing and tracking by investigative forces seeking to identify illegal activities. For example, there is a need to automate the process of detection of informative patterns in human trafficking, and especially sex trafficking. Ubiquity of the Internet provides the perpetrators, who take advantage of trafficking victims, with the ability to solicit services on advertisement web sites. This data is publicly available and contains information potentially useful to law enforcement investigators to understand crime patterns and to track the perpetrators. This team proposes to study the commercialization opportunity of a prototype analytic tool which they developed for the task. This technology may save time and increasing law enforcement productivity and effectiveness by providing new leads that would otherwise be missed.This project provides a framework for demonstrating practical utility of machine learning research previously funded by NSF in a well-focused context of its societally important application. The proposed innovation has the potential to revolutionize the investigative process in the US at local, state, and federal levels. The vast amount of data online is currently underutilized. This project seeks to remedy this for general benefit of society. It would improve efficiency of law enforcement practice at all levels (local, state, federal), facilitate cross-agency collaboration, as well as enhance public policy studies. The proposed innovation will also have a broader application in leveraging public sources of data for detection and mapping of patterns of other illicit behaviors (e.g. sale of stolen and counterfeit goods) and non-illicit behaviors (e.g. economic activity, job seeking, lifestyle, and public health).