Most police forces have a process whereby this raw information is groomed into maps by a central crime analysis unit.   Determining where hotspots are present and describing  recent events is definitely useful, but how can we accelerate this process to adapt our analytic output in nearly real-time and then disseminate this information to the field?

The answer is by automating the flow of information.   We see this feature as a core strength within our product, HunchLab.   New information is automatically pulled into HunchLab through integration with police agencies computer aided dispatch (CAD) and records management systems (RMS).   This new information is then immediately incorporated into analytic output.     New incidents can trigger early warning alerts for spikes in activity or modify short-term risk assessment in a particular police district.   But it’s not just about consuming this information within HunchLab itself.    The system provides secure access to analytic output via APIs that can be integrated into other back-end applications, further analytic tools, and even mobile applications.

To learn more about our vision for the real-time police force, you can watch the webinar recording embedded below:

Below, you’ll find a webinar recording that discusses the early warning system within HunchLab.   Robert and I discuss how the user interface guides the user through creating saved analyses — the Hunches that give HunchLab its name.   We also discuss some of the underlying statistics that power the data mining process.

You might ask:   Jeremy, what is RTM all about?

The concept of RTM is to forecast risk based on the context within which crime incidents occur.  One of the strengths of RTM is it’s relative simplicity, which results in easy to understand models.

Let’s say that we notice that shootings seem to frequently occur near public housing and in areas with a high density of drug incidents.   While we can’t necessarily say that these risk factors cause the shootings, we can statistically test whether there is correlation present in the data.   We convert these two risk factors into two GIS raster layers — a representation of each dataset as a landscape of risk values.   We then combine the two risk layers to form one landscape — our RTM.   The model can then be used to prioritize areas in which to address shootings in the coming weeks and months.

Thus far, RTM has been largely a manual process in desktop GIS tools.   Our compendium chapter addresses how moving to a server-based approach to RTM could tranform its application.   By dramatically reducing model computation time, a user can interact with RTM quite differently — testing more datasets, generating multiple models from which to choose, and even publishing interactive models on mobile devices such as tablets and smartphones.

You can download the Compendium PDF from: http://www.rutgerscps.org/rtm/

An excerpt from Chapter 29: “Transforming RTM with Server-based Geoprocessing”:

Recent advances in computing and spatial analysis technology—namely distributed processing and mobile technology—make it possible to implement an intelligence-led policing model, such as ACTION, more comprehensively.

Azavea’s ongoing research to optimize GIS data processing performance by distributing computation across multiple threads, processors and servers demonstrates the potential to make RTM available as a scalable, web-based application. This would provide a number of advantages to law enforcement agencies.

First, it would make the automated application of RTM simultaneously available to multiple users across a network.

Second, it would provide faster processing and response times even with large datasets or greater geographic extents, enabling crime analysts to more easily experiment with and fine-tune models.

Third, and perhaps most importantly, it would enable the display of interactive risk terrain maps on mobile devices and make them available to officers in the field, where they could be updated on-the-fly based on current conditions.

This chapter will outline several potential approaches to enabling processing to occur with sufficient speed that an RTM application could be deployed to a much broader audience within a police department.

This is a rather technical dive into the near repeat pattern analysis and load forecasting features that we’ve built into HunchLab.  Both of these features are aimed at helping a law enforcement agency to better predict risk levels across their jurisdictions and allocate resources according.    While no application of predictive analytics will be perfect, forecasting risk based on models of the past can help officers and analysts to anticipate the appropriate next steps.

Near repeat pattern analysis helps officers quantify the risk that arises from multiple incidents happening close to one another in space and time.    What we are quantifying is how the fact that your neighbor’s house is burgled raises your risk of a burglary in the coming days and weeks.

With load forecasting we are looking at cyclical temporal patterns in incidents.    How does the time of year, time of day, and day of week change the levels of crime incidents that we should expect across a jurisdiction?   By modeling these cyclical patterns we can project crime levels into the future, helping law enforcement agencies to allocate resources appropriately as well as better manage organizational accountability.

A few months ago I stumbled upon the Geckoboard product which provides a slick SaaS dashboard publishing system.   It had prebuilt integrations to a number of services that we use (Google Analytics, Google Adwords, Google Calendars, Pingdom, Mailchimp, and Twitter) and so it was a natural choice to get things started.    Since custom widgets can point to our own data services, we can publish any sort of metric we desire to.

You can get a sense of what this looks like in the snapshot from today above.   I particularly find it interesting to see the ebb and flow of website traffic.   We had a surge in traffic in May, so this month’s web visits are down in comparison to the previous month.   (It makes me wonder when Google Analytics will gain the ability to adjust for cyclical trends like we do in HunchLab).

More recently, we were asked to beta test the new mapping widget that Geckoboard rolled out.   It was pretty easy for two of our developers (Andrew J and Carissa) to generate a feed of recent legislative district matches being conducted via the Cicero API to display on the widget.      Now, it’s almost immediately apparent to the Cicero team when one of our clients conducts outreach in a particular state, since the state becomes covered in blue dots on the map — which is pretty cool.

We’ll be steadily working to publish more metrics on the dashboards in the weeks and months to come, which will find their way onto our spiffy new office metrics display.

While we covered a broad overview of the types of maps and uses for GIS in the nonprofit sector, we didn’t have time to dive into the topics deeply.     If you are interested in how to use geographic analysis to support fundraising efforts, you may want to register for the NTEN webinar that we are presenting this upcoming Thursday (5/19/2011).    You can find more information online here:

http://www.nten.org/events/webinar/2011/05/19/geographic-gap-analysis-leveraging-census-open-and-proprietary-datasets-fundraising

At Azavea, we’ve long realized that by combining highly intuitive interfaces with high performance geoprocessing, we could build web applications that simplify the user experience and push the limits of what is possible with web-based geographic visualization and modeling.   What we’ve realized in the process is that delays in user input impact the accuracy of the models and forecasts that we can produce.   Whether we are forecasting crime levels across a city or modeling watersheds, the millisecond delays of waiting on human button pushing reduces the potential of our software.

By rolling out a system to reduce this human induced error, Chromercise is bound to improve every application that we’ve produced.    Please join us in reaching out to Google to express our thanks for this truly revolutionary program.

I always return from the annual Nonprofit Technology Conference energized to do even more to support the nonprofit sector.  Why?   Because the people are amazing.   They are bringing dictionaries to students, helping people find volunteering opportunities, helping environmental organizations mobilize their communities, ensuring we have safe food and water from farmland that is local, and providing nonprofits with advocacy tools that they need to create change.

I left the nonprofit world a year and a half ago to join Azavea, but I would have never done so if I hadn’t found a company that was dedicated to creating true change which just so happened to be a for-profit.   This is one of the reasons Azavea became a B Corporation a year ago — to demonstrate just how committed we are to improving the community around us.

Azavea is not new to working with nonprofits and change makers.   We’ve helped a theater better understand their ticket buyers and supporters, a public arts program share their collection of murals and keep track of mural conditions over time, a sustainable business organization encourage the use of sustainable transit, and advocacy organizations to engage the public in redistricting through open source tools to name a few.

The projects we take on (whether for nonprofits or not) have three qualities:

• the project has social value
• the project is more than simply putting dots on a map
• the project leverages geography (and typically the web or mobile technology)

Here are four ways that we can help you, as a nonprofit, move beyond dots on a map:

1. Putting Maps to Work:  A Webinar for Nonprofits

My colleague, Tamara, recently put on a series of seminars at NPower PA to demonstrate the different ways that a nonprofit can utilize GIS software.   From helping you to better plan outreach to reporting program outcomes to funders, generating compelling maps can help your organization to tell your story more effectively.   Tamara and I are hosting a condensed, webinar version of the seminar on Thursday, April 21, 2011 from 1-2pm EDT.    Registration is free at the link below and we are planning to cover:

-  Best practices for collecting, managing and sharing geodata
-  An introduction to geocoding
-  An overview of key map types
-  Pointers to free and low-cost resources to get you started with mapping and GIS

2. Leverage Esri’s Software Donation on TechSoup

Azavea is a business partner with Esri, the market leader in geographic information systems (GIS) software.   Like most commerical software, Esri’s products are not free, but thankfully you are a nonprofit and can leverage their donation program on TechSoup which includes training.

Esri has different versions and extensions of their desktop software.   A good starting point is ArcView which will meet most nonprofit needs.  Your nonprofit can request an ArcView license on TechSoup.   The software has a bit of a learning curve if you are not familiar with GIS software, but where there is a will, there is a way. Esri includes online training with the product donation to help you get started and when you are ready to jump to web-based geographic analysis, we can help you figure out the right mix of software technology that will best meet your needs.

3. Leverage Azavea’s Cicero API Donation on TechSoup

A few years ago we built an elected official district matching API to meet the needs of a local nonprofit arts advocacy organization.  Greater Philadelphia Cultural Alliance wanted to reach out to city council members but there wasn’t a way to match an address to a council district and thus was born the Cicero API.     Today, the API provides true geographic district matching for 100 US city councils, state and federal legislatures, as well as non-legislative districts such as watersheds, school districts, and police districts.   Cicero has been used to power legislator look-up tools on websites, stamp databases with electoral districts for reporting, and power advocacy calls-to-action.

We’re pleased to announce that we are bringing the Cicero API to TechSoup Stock in a few weeks.   Stay tuned for more information or drop us a note to be notified when the donation program rolls out on TechSoup Stock.

Update:  You can find the Cicero API listed in TechSoup Stock here.

4. Nonprofit GIS Brainstorming & Assessments

Sometimes it’s hard to know where to get started and having the knowledge of what is possible and what questions to ask can help immensely.    We believe in being generous with our time, and are more than happy to spend an hour of our time answering your GIS questions or bouncing around the mapping idea you have.

Drop us a note and say hello, we’d love to get to know you better.

• Geographic Gap Analysis: Leveraging Census, Open, and Proprietary Datasets for Fundraising
• Behind the Vendor Curtain: Technology Tips and Lessons Learned from Socially Minded Companies