Guest blog by Andrew Webster, M.S., ASA, MAAA
It was the summer of 2015. I had founded my company, Validate Health, one year earlier. The Society of Actuaries awarded me $10,000 for the summer to sponsor a non-traditional internship. My intern, Nate, and I found a project working directly with a group of physicians to help them improve their payment under risk contracts. This was Validate Health’s first significant project working with a healthcare provider customer. If we were able to convert the summer project into an ongoing relationship then we could raise investor funding. The stakes were high.
We needed to import claims and medical record data, evaluate reserving models and mine the data for patterns of excess medical cost in a short one-month project. By the end of the project, I wanted to have a web-based tool so that we could charge monthly subscription fees. All of the analytical work was done using R since that was what Nate and I had both used at University of Wisconsin. I planned on using the Ruby on Rails web framework for connecting to R to implement the online tool. I was unable to afford an R Shiny license.
The month progressed quickly. We spent three of the four weeks dealing with data issues. By the last week, we were finally evaluating models and pinpointing areas of risk-adjusted high cost. I did not have time to connect Ruby on Rails and R. We had to cut and paste screenshots of R visualizations into a PowerPoint presentation only hours before the final meeting.
Then we met with the Chief Operating Officer and Vice President of Population Health for the physician group. The meeting did not go well. We uncovered reimbursement issues with the chronic obstructive pulmonary disease patients using association rule learning. Additionally, we reverse engineered one of the insurer payment formulas. Those insights were valuable to the customer. However, when they asked questions regarding the end stage renal disease patients and why our reserving factors were high, we were unable to answer on the spot. That was the last meeting with the customer. I later learned that they purchased a software program to replace much of the modeling that we had done.
By the fall of 2015, my company had exhausted our funding. I went to a tech Meetup to find a temporary tech job. Coincidentally, I met a tech founder who had successfully founded three companies. As I talked with him, he revealed that one of the secrets to his success was using Python for both web development and analytics programming. I had used Python before for various scripting tasks but had never thought of it as a strong web programming or statistical programming language. If Python were the bridge between web development and analytics, then I no longer needed to struggle with connecting R and Ruby on Rails. As I researched further, I found that other successful Chicago tech companies such as Procured Health, Apervita and Spot Hero were using a pure Python development stack. Indeed, Python had matured into both a leading web framework and statistical programming language.
From that point on, all of our programming was done in Python. By early 2016, Validate Health won the Chicago Python pitch competition and solidified its reputation as a Python-based health InsurTech company. We received funding to attend the annual Python conference and pitch to Google, Yelp and the original founder of Python. Using Python enabled us to rapidly develop dozens of analytics applications at low cost. As of late 2017, Validate Health has nearly half a dozen customers with a strong growth trajectory for 2018. All analytics are automated using Python and give hands-on control to our customers through a web-based interface. We could not have reached the stage that we have if we continued to use R and Ruby on Rails. Python saved my company!
Join me on my webinar on November 2nd to learn the joys of analytics programming using Python. The initial session focuses on installing the Python analytics stack, explaining how Python is different than other solutions and the wide array of data operations that Python automates. The second webinar is January 17th and will cover advanced data analysis techniques in Python.
About Andrew M. Webster, M.S., ASA, MAAA
Founder, actuary and licensed broker at Validate Health, a member company of the HealthTech incubator MATTER in Chicago, IL. Validate Health provides cloud-based actuarial analytics and reinsurance procurement services to Accountable Care Organizations. Andrew is also webmaster and predictive analytics track lead at the Chicago Actuarial Association, mentor for the Society of Actuaries non-traditional internship program and co-organizer of the Chicago InsurTech Meetup.
Andrew has been writing Python code since 2008 when he was employed as a software programmer at a leading Electronic Medical Records software company. He has used Python to scrape websites for data, automate data migrations, perform data analytics, fit statistical models and write website applications. His company, Validate Health, was named one of twelve Python-based companies selected for the 2016 PyCon Startup Row. Andrew believes that Python will be a valuable skill for Actuaries to master for future employment in emerging InsurTech jobs