Tag Archive:
Law Enforcement

Mining Data for Safer Communities

By Published in 

While a key part of the open government movement is releasing raw data, data on its own is not transformative.   Synthesizing data to gain insights into the communities in which we live is really the key.   This progression to a data-driven society is not only important for those outside of government but also departments within government.

A good example of driving decisions with data is how police departments have leveraged crime data to better police our communities to improve public safety.  Most police agencies examine historic crime data to determine where and when crime hot-spots are occurring and then deploy their resources to react to the changing environment.    Departments are beginning to go beyond looking at simply the dots on the map to also determining what is occurring that is unusual, as well as modeling crime to forecast risk in the coming days and weeks.    It is impossible to address an emerging crime problem without first identifying that something unusual is occurring, and with departments producing ever more volumes of data, law enforcement agencies need tools to automatically sift through datasets to produce synthesized information upon which they can act.   Ideally, this information can also be shared with the public to further accelerate its impact on fighting crime.

We invite you to join us at our next webinar to learn how HunchLab helps police agencies to better protect our communities by mining through historic data and alerting officers when something unusual is occuring in their assigned area.

Please register to join us on Wednesday, August 24, 2011 from 1:00 PM – 2:00 PM EDT:

Tags: , ,
Print This Print This Comments (0)

HunchLab: New Face, New Features for Improved Visualization

By Published in 

hunchlab_logoHunchLab, our web-based geographic crime visualization, early warning and risk forecasting software just got a makeover.  As we continue to venture further into new avenues of crime analysis, it’s clear that the ‘big picture’ is rarely just a photo taken from above.  There are many methods for visualizing raw statistics, conducting point analysis, and reporting on the findings. We continue to research the latest methods and have built the strongest of these into HunchLab. These powerful new visualizations are also inspiring new functionality.  Over the past several months, we’ve been exploring application dashboard interfaces which allow for the straightforward display of the results of complex analysis.

Hunchlab Dashboard View

HunchLab's Intelligence Dashboard

HunchLab began as an early warning system that can detect changes in the geographic clustering crime events and then subsequently notify a geographically specific list of users when an emerging cluster is detected.

We have now extended HunchLab to not just help you find hidden trends, but also to visualize the key metrics of your organization.  With the new Intelligence Dashboard, any HunchLab user can interactively view key trends and patterns.

Toward Risk Forecasting
The ‘hunch’ in HunchLab comes from what is known as ‘Abductive’ reasoning.  It is the method of combining intuition (a hunch) with facts towards the production of actionable information.  One of the best known supporters of ‘abductive’ reasoning was the character Sherlock Holmes, a great crime solving inspiration for us here at Azavea.  He might have well been talking about HunchLab when he said “We balance probabilities and choose the most likely.  It is the scientific use of the imagination.”* Although every great crime solver must focus on the circumstances of the individual event, HunchLab is built to examine the aggregate, the big picture.  Its historical statistical analysis has focused on locating spikes and anomalies in the data from the recent past, but what about the future?

Hunch Details View

A point map shows the incidence of crime in a designated geographic area. The Time-of-Day/Day-of-Week chart shows the temporal density of the events that occurred during any particular hour within that timeframe.

The most natural and challenging extension of HunchLab is that of risk forecasting.  We’re investigating the use of volumes of historic data and the best available techniques towards the goal of making certain types of forecasts available to every HunchLab user.  It’s worth noting that we are not pretending we or HunchLab can predict the future.  Perhaps it’s better expressed by Mr. Holmes who said, “while the individual man is an insoluble puzzle, in the aggregate he becomes a mathematical certainty.  You can, for example, never foretell what any one man will do, but you can say with precision what an average number will be up to.  …  So says the statistician.” **  You are probably wondering where we are going with this.  We hope to roll out the specifics over the next year, but we are actively working with criminologists, statisticians and geographers to create a few different types of forecasting approaches including:  near repeat patterns; daily workload forecasting based on shift, day-of-week and season; the impact of non-crime events, such as weather, holidays and sports events; and generation of risk maps based on a variety of factors.

Come talk to us about HunchLab at:

Int’l Assoc. Law Enforcement Intelligence Analysts Conf. (IALEIA) in Orlando, FL – May 3 – 7

Law Enforcement Information Management Conf. (LEIM)  in Atlanta, May 24 -27.

* The Hound of the Baskervilles
** The Sign of the Four

Tags: ,
Print This Print This Comments (0)

HunchLab: Heat Map and Kernel Density Calculation for Crime Analysis

By Published in 
Hunchlab_heatmap_timeday

Results for a “Hunch” set by a user with crime points overlaid on a heat map that shows crime density in a geographic area of interest. The Time-of-Day/Day-of-Week chart below shows crime density at various points in time at that location.

The purpose of HunchLab, Azavea’s geographic early warning system, is not only to identify changes in the geographic patterns in crime and alert users about detected crime spikes, but also to help users analyze and make sense of information about those spikes.

The “Hunch Detail” section of the application provides several tools geared for exactly that purpose. For the past several months we have made significant changes to it.  In addition to thematic mapping and Time-of-Day/Day-of-Week graphs, the latest upgrade provides a heat map layer.  This feature provides a visualization of crime density in a hunch’s geographic area during a specific timeframe.

When designing this new feature, we faced the question of how to best determine density. One way would be to divide an area into square cells and take a simple count of crimes per cell, but these results may not give a clear indication of actual crime density.  If there are two different cells, neither of which contains any crime points, then the density values for both will be zero.  But if one is in the middle of an area with no crime, while the other is adjacent to a cluster of crimes, this difference should really be reflected.  So HunchLab makes use of a more sophisticated process known as “kernel density estimation” which overcomes this problem

“What is kernel density analysis?” you may ask.  Well, rather than treating each crime event as if it only impacted the exact point where it occurred, the effect of each event is spread over the surrounding area.  The distance over which the effect is spread can vary and is specified by a parameter known as the “search radius”.  A “kernel” defines the pattern to use for distributing the event’s impact.  Several kernels are available, each with a different pattern.  The simplest kernel distributes the impact uniformly over the surrounding area, but most use mathematical formulas to give a greater weight closer to the crime event itself.

We’ve not only added this new density calculation feature to HunchLab but also made it into a reusable library that we can add to other applications.  The new library leverages the Azavea Raster Grid (ARG) format already developed for Azavea’s DecisionTree product as well as other investments from previous projects.  In HunchLab, users can adjust several parameters, such as the search radius to use during analysis and the rendering approach to use for displaying the results (equal interval or quantile).  The heat map layer is just one of several tools available to help users analyze the crime spikes that HunchLab detects, with even more on the way!

Tags: ,
Print This Print This Comments (0)

Conference Report: 10th Crime Mapping Research Conference (CMRC)

By Published in 

CrimeMappingConferenceLogoThe 10th Crime Mapping Research Conference was held August 19 – 22, 2009 in New Orleans.  The CMRC is organized every one to two years by the Mapping and Analysis for Public Safety (MAPS) office in the National Institute of Justice.  The CMRC brings together academic researchers, crime analysts and command staff to review the state of the art in geographic analysis and visualization of crime.  This was a lively group with a number of high quality talks and workshops, and a strong series of research-oriented presentations.  While sponsored by the NIJ in the U.S. Dept. of Justice, attendees included folks from Japan, Turkey, Canada, and the UK.

While there were several interesting presentations, I would like to highlight four that I particularly enjoyed:

I attended two presentations by Dr. Elizabeth Groff, a Professor of Criminal Justice at Temple University.  In her keynote address, she suggested that while our ability to visualize crime patterns has steadily improved, there is a difference between information and “actionable” information, and, as a community, we need to be creating more tools that are aimed at generating actionable intelligence.  She set out several examples of what this might look like in different operational contexts.  I was very proud that one of her examples was Azavea’s prototype for HunchLab, the Crime Spike Detector currently in use at the Philadelphia Police Department.  Dr. Groff also did a fascinating presentation introducing the use of Agent-based Modeling and how this simulation technique can be applied to modeling geographic patterns of criminal behavior.

Hunchlab_points_heatmap

Dr. Wilpen Gorr, from Carnegie Mellon University, presented a paper on Receiver Operating Characteristics (ROC) for Hot Spot Analysis.  ROC was a technique originally developed for analyzing radar signals and has since been used in medical imaging, but crime analysis is a novel application.  He has been working with the technique to calibrate kernel density smoothing as well as to use leading indicators to create predictive analytics for particular classes of crime.

Jerry Ratcliffe, a colleague of Liz Goff at Temple University, also did multiple presentations.  The one I attended was on a pattern his team has been researching, called the “near repeat” effect.  He has demonstrated that for some crimes, like burglary, there is a “contagion” effect that raises the likelihood of a repeat crime occurring near the original crime within a short period of time after the event.  His work does not end with a research paper – he has built some helpful software tools to help calculate the extent of the effect.

In summary, this was a terrific event, and I have to commend the Director of MAPS, Ron Wilson, and his colleagues for creating an excellent forum for exchanging ideas.

Tags: ,
Print This Print This Comments (0)

What is PhillyStat?

By Published in 
"... what really gets us jazzed is the central role that GIS and statistics play in the [PhillyStat] process."


Beginning in the mid-1990′s, the New York Police Department, under William Bratton, Jack Maple and John Timoney, created a system that became known as CompStat, short for ‘computer statistics’. Under this program, precinct commanders met on a regular basis with the NYPD executive team to review statistics and conditions in their precincts. Despite the name, in some sense, CompStat had nothing to do with computing. It was an organizational management tool for law enforcement agencies. The key innovations were measurement of results, regular review, and relentless follow-up. All of these activities were directed at performance and accountability with lower levels of crime being the key performance metrics. But computing, and GIS in particular, played an important role. GIS software had become sufficiently inexpensive and easy to use that it could be run on desktop PC’s. Maps and stats became the mechanism by which the results would both be measured and reviewed. CompStat would become inextricably associated with mapping and GIS.

The results were spectacular. Over the course of several years, New York City saw dramatic drops in crime. Obviously, this could not all be attributed to CompStat – there were many factors – but the idea was conceptually simple and clearly brought results, setting the stage for its replication in other parts of the country. When Bratton, Maple, and Timoney left the NYPD, they took the program to Philadelphia, Los Angeles, and Miami, and it was quickly picked up by other cities. Baltimore took the process one step further, extending the performance management concept to all municipal agencies to create CitiStat. Similar programs now exist in Chicago, Washington DC, San Francisco, and dozens of other cities. In 2006 Washington DC added an important innovation: live data feeds for much of its operations. Why was this important? Good government is frequently related to the degree of transparency provided to the public. DC took a huge leap toward greater transparency by making its actual operational information freely available to all.


Philadelphia’s new Mayor, Michael Nutter, made implementation of a CitiStat program a key part of his election campaign and began implementing the concept within weeks of taking office. PhillyStat was launched in March.

Why does Azavea care? Well, there’s obviously the abstract sense that our tax dollars are being more effectively spent and that these efforts may eventually result in better city services. But what really gets us jazzed is the central role that GIS and statistics play in the process. The meetings are open to the public, and having now attended a couple of the PhillyStat meetings, I am amazed by the range of maps and data being used to more effectively communicate and collaborate. People are not just making maps of crime, but using aggregated maps of deeds and mortgages to examine the impact of foreclosures, examining the changing geographic patterns real estate tax to understand how the real estate market is changing in each neighborhood. Having just rolled out the new public crime mapping application in Philadelphia, I’m also looking forward to seeing the PhillyStat data made available to the public.

Tags:
Print This Print This Comments (1)

Philadelphia Police Department Makes Crime Mapping Application Available to the Public

By Published in 
"People like to know what goes on in their neighborhoods ... they want to know if any crimes have been committed nearby."

People like to know what goes on in their neighborhoods. Most of us want to know if a new family is moving in down the block, if a store is closing or a new business opening, and, perhaps more than these, we want to know if any crimes have been committed nearby. And when it comes to something as important as crime, we want that information from a credible source. While police departments across the country record this information, it is generally only used internally by police personnel. In recent years a relatively small number of city police departments have started making the data available to the public.

Philadelphia’s Police Department (PPD) is now one of these select police departments. In response to widespread public concerns about crime in the city, Mayor Nutter and Police Commissioner Ramsey charged the Police Department with creating a public website where city residents can map the incidence of major crimes in Philadelphia. Based on our previous work with crime analysis applications (such as Crime Spike Detector and PhiCAMS), the PPD selected Azavea to develop the system. Working closely with the Police Department and the Mayor’s Office of Information Services (MOIS), we were able to get the application up and running in just six weeks.

The emphasis of the site is on simple, accurate display of crime occurrence across the city in a “pin map” style. All crime data is fed nightly to the site directly from Philadelphia Police Department’s databases. Up to 30 days worth of crime can be viewed simultaneously and a data download feature enables anyone to extract and download the data for more rigorous analysis.

One of the greatest challenges in creating the site was the need to display even relatively high volume of crimes at every scale. For example, theft is the most numerous of the so-called “Part 1″ crimes (the more serious crimes). Viewing thefts city-wide, for a typical thirty-day period, may result in 3,000 or more data points. The map depicting this situation would simply be a mass of undifferentiated points, which is not useful to anyone.

To address this concern, the site uses a common cartographic technique of “aggregation” – taking many points concentrated in the same geography and lumping them together into a single larger point, sized proportionately to the number of points it represents. This is analogous to the size of points used to represent the population of cities in many atlases. The website computes these new aggregations “on-the-fly” depending on how close or far one has zoomed into the map. There are several techniques for accomplishing this type of task. We used the ‘K-means clustering‘ approach which is a method for finding the centers of natural clusters.

We are excited by this new initiative and hope the public will find it useful. Visit http://citymaps.phila.gov/crimemap to check out the application or your neighborhood.

Tags: ,
Print This Print This Comments (0)

Azavea Wins Another Prestigious SBIR Award from NSF for HunchLab – Leveraging Spatial Statistics to Validate Human Intuition and Fight Crime

By Published in 
"The ability to detect and analyze changes in the geographic patterns of crime and disorder is an innovation in policing which holds the potential to enhance the organizational capacity of police departments across the country."

Just over a year ago, we proudly announced that Azavea had been awarded a Small Business Innovation Research (SBIR) Phase I grant from the National Science Foundation (NSF) for the development of our HunchLab product, a set of innovative software tools that scour the current and historic data of a police department, search for changes in geographic patterns, apply spatial statistics to test for significance, and send alerts to relevant law enforcement personnel. Today, we are thrilled to announce that NSF has awarded us Phase II funding to further development of this software and its commercialization.

Our Phase I project proved the feasibility of building the application, and the Phase II project will refine the application and build additional functionality, including alternate workflows for different user types, developing a new user interface, expanding the alert infrastructure, and building text mining capabilities. The result will be a commercial version of the software.

Preventing crime is a more sophisticated task than simply mapping incidents or arrests and deploying resources accordingly. The ability to detect and analyze changes in the geographic patterns of crime and disorder is an innovation in policing which holds the potential to enhance the organizational capacity of police departments across the country.

HunchLab was inspired by the Crime Spike Detector that Azavea developed to help the Philadelphia Police Department identify when and where unusual increases in crime are occurring. Read our white paper for more information. The Crime Spike Detector, which has been in operation since June 2005, uses a spatial statistics algorithm developed in conjunction with Dr. Tony Smith (University of Pennsylvania) to compare current crime to historical crime across the city. Each night this ‘data mining’ service checks for spikes in different types of crime. Unusual increases result in an email being sent to the relevant district captain. The email details the severity of the spike and links to an online report with maps, charts and tables, enabling analysis of the result. .

Although HunchLab will initially be developed to assist with crime detection, tools such as the Spike Detector and HunchLab are applicable in any application where events display geographic changes in distribution, such as disease occurrence, consumer buying patterns, real estate sales, and property and mortgage fraud.

HunchLab is supported by the Small Business Innovation Research program of the National Science Foundation, Directorate for Engineering, Division of Industrial Innovations and Partnerships, Award Number (IIP-0750507).

This is the fourth time in two years that Azavea has been awarded an SBIR grant. Previous awards were SBIR Phase I awards from the National Science Foundation, the U.S Department of Education and the U.S Department of Agriculture.

Tags: , ,
Print This Print This Comments (0)

Tracking the Fraud-ulators with GIS

By Published in 
"...it will be an important new tool for the City, legal professionals, and law enforcement to fight property fraud."

Photo courtesy of PhillyHistory.org, a project of the City of Philadelphia Department of Records.

As if declining home sales, a credit squeeze and predatory lending practices were not enough, there has been a substantial rise in mortgage and deed fraud throughout the boom and bust of the real estate market. While this trend has been most apparent in the hottest real estate markets, Philadelphia’s homeowners have not been spared from this crime. The methods run the gamut from simple to complex, seemingly innocent to downright treacherous. But the outcome of what is known as ‘property conveyance fraud’ is often the same — a homeowner is bilked out of their equity or the deed to their home. The City of Philadelphia has been combating this phenomenon with a multi-agency task force organized by the Philadelphia Bar Association. The Property Conveyance Task Force is an ad hoc committee of City agencies, law enforcement officials, title insurance companies, non-profit legal assistance organizations, and the district attorney’s office. The group meets every few months to discuss and share information on fraud schemes and develop strategies for detecting and mitigating the damage.

The task force has made progress in terms of developing strategies, but the most serious impediment remains the lack of information available to all members of the group. Azavea was asked by the City’s Department of Records — where deeds and mortgages are recorded as legal documents — to help develop a GIS-enabled fraud tracking system. The result is a set of web-based tools that use ESRI’s ArcIMS map server and the City’s web services API’s to enable all members of the task force to register fraud reports, search the results, and subscribe to geographic alerts. While it will not be available to the general public, it will be an important new tool for the City, legal professionals and law enforcement to fight property fraud.

If you are interested in learning more about the effects of property conveyance fraud, there was a series of articles in the New York Times last year that may prove interesting:

“Mortgage Fraud Is Up, but Not in Their Backyards“

“New Scheme Preys on Desperate Homeowners”

“Fraud Cases Are Rising, F.B.I. Says”

Tags: , ,
Print This Print This Comments (0)

A “SMART” Puzzle

By Published in 

The SMART System of the US Department of Justice’s Office of Juvenile Justice and Delinquency Prevention (OJJDP) makes a wide range of data available to anyone interested in and professionals involved in identifying, halting, or preventing juvenile delinquency.

Let’s say that you represent an organization in Pennsylvania that is working to curb juvenile crime, and you’re going to use the SMART System to apply for a grant relating poverty to crime. Register with the SMART system, then press the Mapping and Analysis button (no search text is required) and choose Pennsylvania > Counties. Then choose the ‘Economic’ indicators that will help you answer the following questions:

1. Using the map, what County in Southeastern Pennsylvania sticks out as having a disproportionately high percentage of children living in poverty?

2. What three counties have the highest percentage of families living in poverty (use most recent indicator data)?

3. Using the appropriate ‘Crime’ indicators, answer the following question: Name the three counties reporting the highest juvenile crime rate.

Be the first to send an email with all three correct answers to info@azavea.com and we will send you a $20 gift card to Barnes & Noble!

Tags: , ,
Print This Print This Comments (0)

OJJDP Implements SMART On The Kaleidocade Platform

By Published in 
"Kaleidocade brings ... data ... to the people who need it, in a way they can easily understand, summarize, and analyze. "

Azavea announces the public release of the first national-scale implementation of our Kaleidocade Indicators Framework (KIF): The Socioeconomic Mapping and Resource Topography (SMART) system, developed for the U.S. Department of Justice, Office of Juvenile Justice and Delinquency Prevention (OJJDP). Kaleidocade is a unique web-based software framework used for visualizing geographically aggregated data as maps, tables, charts, statistics, and trends, which fit perfectly with OJJDP’s requirements.

The OJJDP supports state and local juvenile justice systems and programs nationwide, and sponsors research and training related to juvenile justice issues. In order to more effectively match resources and needs, they sought to develop a system that would merge a wide range of data sources such as demographics, crime, risk factors, education, economics, and grant resources, to support the identification of emerging issues and assist decision makers in developing appropriate responses.

Azavea, under subcontract to Development Services Group, Inc. (DSG), implemented the Kaleidocade framework, which uses ESRI’s ArcIMS, ArcGIS Server and ArcWeb Services for mapping and geocoding functionality. OJJDP required a tight timeline and Phase I was finished and installed in 6 weeks. Phase II, which contains enhancements, is ongoing. SMART currently contains over 3.3 million rows of demographics, economic indicators, educational data, youth risk factors, and statistical indexes—more than 100 different indicators aggregated to states, counties, and census tracts throughout the entire United States. Kaleidocade brings all of this data to the people who need it, in a way they can easily understand, summarize, and analyze.

To view the SMART application, visit http://smart.gismapping.info. For more information on Kaleidocade, please visit www.azavea.com/products.aspx or contact info@azavea.com.

Tags: , ,
Print This Print This Comments (0)

SBIR Grant Award Announcement: HunchLab – Leveraging Spatial Statistics to Validate Human Intuition

By and Published in 

As part of their daily activities, police officers often formulate hunches based on observations and other sources of information. Large amounts of crime data already exist in electronic form, so officers have been using information management systems and visualization tools to help sift through this data. Despite the availability of these tools, hunches remain difficult to confirm or deny.

We are pleased to announce that the National Science Foundation recently awarded Azavea a Phase I Small Business Innovation Research (SBIR) grant to design and evaluate ‘HunchLab’, a prototype system that will enable police officers to develop and evaluate hunches.

‘HunchLab’ was inspired by the Crime Spike Detector that Azavea developed to help the Philadelphia Police Department (PPD) identify when and where unusual increases in crime are occurring. The Crime Spike Detector, which has been in operation since June 2005, uses a spatial statistics algorithm developed in conjunction with Dr. Tony Smith (University of Pennsylvania) to compare current crime to historical crime across the city. Each night this ‘data mining’ service checks for spikes in different types of crime. Unusual increases result in an email being sent to the relevant district captain. The email details the severity of the spike and links to an online report with maps, charts and tables, enabling analysis of the result (learn more). Although ‘HunchLab’ will initially be developed to assist with crime detection, tools such as the Spike Detector and ‘HunchLab’ are applicable in any application where events display geographic changes in distribution, such as disease occurrence, consumer buying patterns and real estate sales.

‘HunchLab’ is supported by the Small Business Innovation Research program of the National Science Foundation, Directorate for Engineering, Division of Industrial Innovations and Partnerships, Award Number (IIP-0637589).

Tags: , ,
Print This Print This Comments (0)
Copyright © 2001 - 2012; Azavea. All rights reserved.
340 North 12th Street, Suite 402
Philadelphia, PA 19107.
Tel: (215) 925 - 2600 Fax: (215) 925 - 2663

 
  • Azavea Journal
  • Azavea Atlas
  • Azavea Labs
  • Azavea.com