In anticipation of his upcoming conference presentation, Acquisition Funnel for Higher Education at Predictive Analytics World for Business New York, Oct 29-Nov 2, 2017, we asked Feyzi Bagirov, Data Science Advisor at Metadata.io and Analytics Instructor, Harrisburg University of Science and Technology, Becker College, a few questions about his work in predictive analytics.
Q: In your work with predictive analytics, what behavior or outcome do your models predict?
A: Some of the models we use at Metadata.io are used to predict customer lookalikes – identifying the common qualities of the customers who are likely to be interested in your business because they are similar to your best customers in the past.
We have a patented technology that uses predictive models to identify which micro-experiments (agile marketing campaigns) yield the highest ROI (normalized score) and then chooses the 15-25% winning campaigns, re-calibrating/continuing to optimize the funnel with new experiments.
We also use both supervised and unsupervised machine learning models to classify and normalize data that has multiple categories – industries, skills, job titles, etc.
Q: How does predictive analytics deliver value at your organization – what is one specific way in which it actively drives decisions or operations?
A: Trying to automate a B2B demand generation platform requires a lot of effort. Understanding who is the best potential client allows our clients tremendous savings on marketing campaigns.
Q: What surprising discovery or insight have you unearthed in your data?
A: I’ll start with a non-surprising and used up aspect – cleaning and normalizing unstructured categorical data can be daunting task. How would you categorize “CAO” – Chief Analytical Officer, Chief Academic Officer or Chief Architect Officer?
Some of the surprising discoveries were that many unorthodox titles, for example “Chief Happiness Officer”, are so common, they can easily be considered a valid new category.
Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.
A: Be realistic to narrow the scope of the predictive modeling work at the initial stage; evaluation of models should be in the process; building data structure is more important than methodology
Don’t miss Feyzi’s conference presentation, Acquisition Funnel for Higher Education on Monday, October 30, 2017, at 3:05 to 3:25 PM at Predictive Analytics World New York. Click here to register to attend. Use Code PATIMES for 15% off current prices (excludes workshops).
By: Eric Siegel, Founder, Predictive Analytics World
Eric Siegel is the founder of Predictive Analytics World (www.pawcon.com) — the leading cross-vendor conference series consisting of 10 annual events in New York, Chicago, San Francisco, Washington DC, London, and Berlin — and the author of the award-winning book, Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die – Revised and Updated Edition, (Wiley, 2016).