By: Greta Roberts, Conference Chair, Predictive Analytics World for Workforce 2016
In anticipation of his upcoming Predictive Analytics World for Workforce conference presentation, Balancing Privacy with Powerful Employee Churn Predictions, we interviewed 
Frank Fiorille, Senior Director of Risk Management at Paychex, Inc. View the Q-and-A below to see how Frank Fiorille has incorporated predictive analytics into the workforce of Paychex, Inc. Also, glimpse what’s in store for the new PAW Workforce conference.
Q: How is a specific line of business / business unit using your predictive decisions? How is your product deployed into operations?
A: The model being presented is deployed to senior level management at Paychex across the country to identify hotspots for turnover in the next six months. Key locations and variables are then analyzed to provide added insight for how the data interacts with current retention strategies.
Q: If HR were 100% ready and the data were available, what would your boldest data science creations do?
A: I think predicting employee engagement would be a groundbreaking model. The topic has such an interest today and being able to tell a business unit or employer “Your engagement is going to trend up (or down) in the next sixth months because of X.” would be a really exciting way to positively impact employees at work.
Q: When do you think businesses will be ready for "black box" workforce predictive methods, such as Random Forests or Neural Networks?
A: In my experience some businesses and business units are there. There are several people I have come across that trust the science and trust the experience of our team that they would deploy the best model we selected. When you develop that level of trust with your partners, it really gives you the freedom to stretch the limits of your skills and talents.
Q: Do you have suggestions for data scientists trying to explain the complexity of their work, to those solving workforce challenges?
A: My advice would be to listen first. Understanding your internal or external customer’s needs should define your actions and goals in your model. They will listen more readily to the complexities of your process once they are sure that you’ve heard them and are responding to their needs. On the flip side, don’t feel you need to share every complex detail with them, either. Sometimes sharing too much information is as bad as not sharing enough.
Q: What is one specific way in which predictive analytics actively is driving decisions?
A: We presented previously on our national retention model that is being used to proactively retain clients that are at a high risk for leaving our services. Simply going after these clients before they entertain the decision to switch to a competitor greatly impacts your ability to influence that decision.
Q: How does business culture, including HR, need to evolve to accept the full promise of predictive workforce?
A: I think the biggest thing, and I think it is happening already today, is when we start using data to make decisions, specifically when it contradicts our gut or instinct. I believe we are comfortable using data when it reinforces our intuition, but will quickly discard it when the two don’t agree. I think the key evolution is when we start trusting data over intuition, not blindly or exclusively, but at certain times when our trust is such that we can let the data prove our experience wrong.
Q: Do you have specific business results you can report?
A: We do have results that we will share in the presentation. Because of the new model deployment and the unique methodology used, the results are promising but harder to quantify.
—————————-
Don't miss Frank’s conference presentation, Balancing Privacy with Powerful Employee Churn Predictions, at PAW Workforce, on Tuesday, April 5, 2016 from 11:15 am to 12:00 pm. Click here to register for attendance.
By: Greta Roberts, CEO, Talent Analytics, Corp. @gretaroberts and Conference Chair of Predictive Analytics World for Workforce