Usually, when I interview someone for this podcast, I have some idea of what the person is going to say. I do my homework, read about the topic, and arrive prepared.
Not this time.
When I asked Adam Bradford, Director of Prospect Development at Columbia University in the City of New York, if he could talk about his presentation at Apra PD 2020 with colleague, David Schemitsch, I had no idea how they had created an app to predict capacity.
Was this a product for sale? Was it proprietary or could others replicate it? And what the heck was it all about? It felt so mysterious and cloaked.
Until Adam spilled the beans!
Listen in as Adam shares his journey to uncovering an extremely valuable dataset that could transform the way craft your capacity ratings. That is, if you can make any sense out of the data file!
Searching for updated data to fuel his capacity rating formulas, Adam stumbled over the Survey of Consumer Finances published by the U.S. Federal Reserve. Full of raw data about real people’s net worth, Adam took the time to untangle and use it. He’s got tips for you.
Then his data scientist colleague, David Schemitsch, grabbed the baton, fired up his R program, and created an algorithm to run an app for predicting capacity, based on the survey data.
“Anyone can do it,” quips Adam. But can you?
Resources Mentioned
Survey of Consumer Finances | Federal Reserve | Adam may have been underestimating his comfort with data when describing this data file. Decoding the column headings could easily soak up your entire weekend. But there is joy in a good puzzle pieced!
Capacity Predictor: A Machine Learning Approach to Ratings | Apra Prospect Development Conference 2020 | Session recording available for sale
David Schemitsch & Closing Remarks | Texas Advancement Analytics Symposium | 2020 | Free on Vimeo
