Request Username
Can't sign in? Forgot your username?
Enter your email address below and we will send you your username
AUTHOR SPOTLIGHT
INFORMS member since 2010
Co-author with Jessica Tisch, Anthony Tasso, and Michael Joy of "The New York City Police Department’s Domain Awareness System," in Interfaces
INFORMS: What inspired you to research this particular topic?
LEVINE: We’re passionate about keeping the public and our officers safe, and finding new ways to use analytics and technology to achieve that goal. The authors of our paper are all NYPD employees, a mix of uniform and civilian, so the content of the paper is something we are immersed in every day.
INFORMS: Did any of your results surprise you?
LEVINE: I was surprised by how well some of the traditional analytic methods held up, such as hotspot policing. Our new predictive analytics methods are definitely an improvement, but it turns out that the traditional techniques had a lot of value. We saw the best results when we blended a traditional method with advanced analytics, a sort of hybrid of old and new.
INFORMS: What is the most important take-away you hope readers will learn from your paper?
LEVINE: I wanted the paper to demonstrate that the NYPD is using state-of-the-art analytics to make New York City both safer and fairer.
INFORMS: How do you define "analytics"?
LEVINE: In general, I think the official INFORMS definition is excellent. When I’m talking to folks who aren’t technically trained, I’ll usually say that analytics is how you take data and make it understandable. That’s broad enough to include both the statistical and mathematical part of the job, along with the softer data visualization and decision science techniques.
INFORMS: Tell us about the process of writing this paper.
LEVINE: It was actually kind of fun—we’re proud of the work we do and we like telling people about it. The writing itself was a collaborative effort with my co-authors, but we also got some great advice and editing from Jack Theurer and Pelin Pekgun (our Edelman coaches).
INFORMS: Why was it important for you to submit to the Edelman competition and publish in Interfaces?
LEVINE: I wanted to make the case for analytics in the public sector. Many of the most well-known examples of analytics are from the business world, and are focused on profit or efficiency. Our field is incredibly versatile, and I think public safety provides some very compelling illustrations of how analytics can improve people’s lives. The U.S. Army’s Edelman presentation was another example in this vein.
INFORMS: How do you yourself keep up-to-date on the latest research in your field?
LEVINE: I learn from a variety of different sources. Journals are one part of it, but I also attend conferences focusing on analytics and criminal justice. Most importantly, the team I manage includes analysts from a range of fields, from biochemists to economists, and they bring techniques from their own training to share with our group.
INFORMS: What does a day in the life of the Assistant Commissioner of Data Analytics for the NYPD look like?
LEVINE: Every day is different. I manage a small team of analysts and we work together on a mix of projects. One day we could be working on a long-term project such as a new predictive policing algorithm, and the next we could be helping out a detective squad with an active investigation. I feel like I’m learning something new every day.
INFORMS: What about your career might surprise us?
LEVINE: I’m actually trained as an astrophysicist. The first big data sets I analyzed were maps of gas in the Milky Way’s disk. Ten years ago, I was stationed out in California’s Owens Valley operating a radio telescope in the middle of the desert!
INFORMS: Are you currently doing any research? If so, can you tell us a little bit about what you’re working on?
LEVINE: We always have something exciting we’re working on. Our newest analytic tool helps NYPD analysts identify crime patterns without having to read through hundreds of written reports. It’s a real time saver, and we expect it to improve our detection rate as well.
INFORMS: When you’re not using your OR superpowers to try to make the world a better place, what are some of the ways you like to spend your time?
LEVINE: I’m interested in board games, both playing them and their mechanics, which I’ve written about for OR/MS Today. I also play soccer in a local league and I’m a big fan of Liverpool Football Club.