Category Archives: Analytics

Amazing Projects in Good Government

I just got back from the AISP conference at the University of Pennsylvania.  That was a very inspirational conference!  We heard from many of the members of the AISP network.  Two should be mentioned: Indiana and Allegheny County, Pennsylvania.  Indiana now has an enabling statute where the analytics office is supported by legislative funding.  They even have a staff of 30 people, including data scientists and analysts.  Meanwhile, Allegheny County has been implementing effective government through data analysis for 20 years.  We heard about how they are focused on the opioid epidemic and how they are using data to combat it in their county.  Both of these jurisdictions have inter-agency data warehouses to do their analytics.  Very inspirational stuff.

Here is the link for the Actionable Intelligence for Social Policy network: https://www.aisp.upenn.edu/

 

Back to Civ Tech

I have the great pleasure to report that I am back in civic technology.  I my new role as a data scientist with the State of Colorado, I will be merging siloed datasets from different agencies to create usable, anonymized data that researchers and policy makers can use to inform public policy recommendations!

Just a bit more about my new position….I am working for the University of Denver as a contractor to the Office of Information Technology for the State of Colorado.  I will be working across the various agencies and with IT and the Colorado Evaluation and Action Lab’s LINC (Linked Information Network of Colorado project).  This is a great opportunity to do important work for the state of Colorado.

Here are a few examples of the kinds of projects that I will be working on:

– Does rapid intervention with runaway children improve outcomes (graduation, criminal convictions/arrest, etc.)?

– What are the primary factors affecting non-custodial parents in the timely payment of child support payments?

What factors are associated with multi-system utilizers of the Colorado health care system?

Google IO Developer Keynote

The Denver Google Developer Group set up a meeting to watch the simulcast broadcast of the keynote by Sundar Pichal and related speeches.  The meeting was held over at GoSpotCheck, a startup doing retail inventory verification using AI and machine learning.

The keynote echoed the expected themes: vision, audio, and AI.  Google is developing the building block technologies to increase the amount of AI and machine learning tools that can be deployed.  This means that they not have AI training boards that can do petaflops of computations, they have new libraries for audio and vision, they have expanded TensorFlow to include more than just tensors/neural nets (i.e., other machine learning algorithms like random forest and support vector machine), and they are creating TensorFlow libraries that will run with javascript.  This means that AI models can be pushed down to Android cell phones and tablets and can also call upon their off-the-shelf tools that they have developed.

Bottom line: Between Caffe2,  TensorFlow, Python, and R, there are an abundance of open source tools to do machine learning.

On the meeting side, I met some great people doing interesting development, and I even won a Google laptop bag as one of the raffle prizes!

Completed Masters in Data Science

I finished my Masters degree in data science from Northwestern University this past week.*  I had a fabulous team for my final Capstone project class.  The group wanted to work on a text mining project, so I recommended using a dataset over at Kaggle on the Meyers Briggs Temperament Indicator.  Our goal was to identify which personality archetype a person was based on a single sentence of a posting.

The the video presentation that we created follows. My portion about the data and model development begins about seven minutes into the presentation:

I handled the modeling portion of the project, and so I created models in both Python and R.  The neural network models used both TensorFlow and Keras, running on the GPU card in my computer.  In addition, I created a naive Bayes and Support Vector Machine set of models.  Then I combined these models into an ensemble, and my final ensemble was significantly better than a random guess.

Now that I have finished the program, I am now looking for data science work.  If you know of an engaging opportunity, please contact me.

*The program has now been renamed Masters of Science in Data Science, but because of my entry date into the program, the name of my degree is Masters of Science in Predictive Analytics.

DNA in Action

I have seen many relatives in Finland.  Here’s a second cousin (whose name I’ll withhold for privacy).  What do you think….is there a family resemblance?

 

The trip was a very interesting one.  I saw my DNA in its many forms, but not obscured with American culture.  And I came away understanding a great deal about myself.  I met many people with whom there was a near-instant bond that transcended culture.  It was obvious within minutes that we were alike even though separated by 100 years and two different cultures.

I’ve always been one to think in contingencies.  Not only have a plan B, but a plan C and plan D.  And I found in Finland a culture that thinks the same ways.   And it became apparent that the climate is so harsh in the winter that failure to think that way killed off those who did not.  It’s no surprise that I have this quality; it’s not really luck, but rather the result of thousands of years of necessity embedding itself as a DNA rule.

If you have a unique heritage, I strongly recommend the experience of visiting the motherland.  You will walk away understanding a considerable amount about why you think the way that you do and what parts of you are from culture and what parts of you are hard-wired.

Thanksgiving Daybreak

It’s just another day here in Dubrovnik, but I know it is Thanksgiving in America. Daybreak was pretty, so I am posting a photo. I really enjoy opening the window to the sounds of the seagulls in the morning. They soon fly off to live their seagull lives and you don’t hear them until the following morning.

tdaybreak