Predictive analytics and driver turnover: A tool to improve retention


Predictive analytics are among us. Data of all kinds are being run through computer models that apply advanced statistics and algorithms to identify significant, repeatable patterns.

In finance, healthcare, insurance, trucking, and many other industries, predictive analytics is used by businesses to solve difficult challenges. At a personal level, it is helping people save time and make better decisions.

Many smartphone apps use predictive analytics to recommend movies and songs, to tag our friends in photos, and to deposit our unwanted email in junk folders.

Gathering direct feedback

In trucking, some industry suppliers use predictive analytics to identify the early signs of driver turnover. In theory, if fleet managers know which of their drivers are most likely to quit, and for what reasons, they can intervene and positively change the outcome.

Some models use data that drivers are not aware is being collected and used for the purpose of identifying their probability of leaving. For example, one supplier has a model that extrapolates more than 1,000 variables from hours-of-service (HOS) data to predict turnover.

It’s easy to understand why HOS data might indicate job dissatisfaction due to fatigue or variability in a work schedule, for example. Where it becomes difficult is to talk to drivers about information that is a prediction but not a measured result.

Increasing engagement

A better approach for predictive analytics is one that engages drivers in a feedback process using surveys . The data collected will be a true reflection of how drivers feel about their careers.

Stay Metrics uses several methodologies to help motor carriers understand how drivers feel about their careers. The methods include 7-day orientation and 45-day onboarding surveys, an annual Driver Satisfaction survey, exit surveys, and a privately branded online rewards, recognition and driver engagement platform.

“We know that behavior follows engagement and surveying drivers both increases their engagement but also gives us important insights into controllable causes of turnover,” says Tim Judge, director of research for Stay Metrics, and the Joseph A. Alutto Chair in Leadership Effectiveness at the Ohio State University’s Fisher College of Business.

Predictive 2.0

Recently, Stay Metrics announced the next generation of our predictive driver turnover model. Developed by Dr. Judge, the model extrapolates data from our full product suite, which has been integrated into a single database, and provides valuable insights — specific to each motor carrier — on why drivers leave their companies.

As much as we value rigor in the form of our statistical analyses, we put even more weight on translating the results into practical strategies that our clients can use to reduce driver turnover.

If you’re interested in knowing about methodologies that engage drivers and how to apply predictive analytics to retain more of your best drivers, please give us a call at 1.855.867.3533 or send us a message at

What to read next