Find Out How Machine Learning Helps Fleets Retain Drivers

Find Out How Machine Learning Helps Fleets Retain Drivers

In Q1 2018, the American Trucking Associations (ATA) found that the annualized driver turnover rate for large fleets was 94 percent.

The issue behind this staggering number is multi-faceted, with the ATA citing the struggle to both recruit and retain quality drivers as two leading causes. A structural issue within trucking also plays a role in the driver shortage: the Bureau of Labor Statistics estimates the average age of a commercial truck driver is 55 years old. This means approximately a quarter of the driver population will retire soon and fleets also face the challenge of not enough young drivers entering the workforce to replace those who are retiring.

How fleets are addressing the driver shortage

One way fleets can address this challenge is through the use of data and machine learning. Trimble’s driver retention model uses data to predict the specific factors behind why a driver might leave a fleet. As with any job, there are certain factors that go into why an employee might leave a company. Trucking is no different and some of the factors fleets need to give attention to include pay, time away from home, load type and region traveled.

By sorting their driver base across this set of criteria, fleets can better identify which drivers are at a high risk for departure. Using the Trimble driver retention model, fleets can harness two uses of machine learning: predictive and prescriptive analytics to proactively address the issues that individual drivers might have. These models demonstrate 90 to 95% accuracy in identifying drivers who are at-risk for departure over a seven-day horizon.

 

How predictive driver retention works

The process all starts with data integration. Trimble draws upon its extensive reach into the data ecosystem to pull essential information such as Hours of Service (HOS), pay and home time to help drive the process. Drivers typically don’t leave an employer based on a single event, so data is normalized and transformed through data science to distill and accurately capture inter-relationships between events.


Trimble’s driver retention model turns driver data into predictors of why a driver might leave and prescribes solutions to proactively address a driver’s issue.

 

After this data is transformed, the Trimble model develops predictors, which are fed into a predictive engine that identifies at-risk drivers and scores risk factors. While predictions are important, it is is also crucial to develop solutions to help remedy the situation. The Trimble driver retention platform includes a prescriptive engine that provides a fleet with actions to help keep a driver. For example, a fleet can proactively address a driver who may be frustrated about home time or has an issue with payroll before it has the potential to cause a driver to leave.

 

Driver retention is just the start

Driver retention is only one of the many ways our customers are using machine learning to drive efficiencies and productivity. Check out our free whitepaper to learn about this technology in more detail and find out how to apply its benefits to your organization.

Ready to address driver retention in your fleet? Contact us today to see how Trimble’s solutions can help you make informed decisions to keep your drivers be safe, productive and happy.

Find Out How Machine Learning Helps Fleets Retain Drivers

In Q1 2018, the American Trucking Associations (ATA) found that the annualized driver turnover rate for large fleets was 94 percent.

The issue behind this staggering number is multi-faceted, with the ATA citing the struggle to both recruit and retain quality drivers as two leading causes. A structural issue within trucking also plays a role in the driver shortage: the Bureau of Labor Statistics estimates the average age of a commercial truck driver is 55 years old. This means approximately a quarter of the driver population will retire soon and fleets also face the challenge of not enough young drivers entering the workforce to replace those who are retiring.

How fleets are addressing the driver shortage

One way fleets can address this challenge is through the use of data and machine learning. Trimble’s driver retention model uses data to predict the specific factors behind why a driver might leave a fleet. As with any job, there are certain factors that go into why an employee might leave a company. Trucking is no different and some of the factors fleets need to give attention to include pay, time away from home, load type and region traveled.

By sorting their driver base across this set of criteria, fleets can better identify which drivers are at a high risk for departure. Using the Trimble driver retention model, fleets can harness two uses of machine learning: predictive and prescriptive analytics to proactively address the issues that individual drivers might have. These models demonstrate 90 to 95% accuracy in identifying drivers who are at-risk for departure over a seven-day horizon.

 

How predictive driver retention works

The process all starts with data integration. Trimble draws upon its extensive reach into the data ecosystem to pull essential information such as Hours of Service (HOS), pay and home time to help drive the process. Drivers typically don’t leave an employer based on a single event, so data is normalized and transformed through data science to distill and accurately capture inter-relationships between events.


Trimble’s driver retention model turns driver data into predictors of why a driver might leave and prescribes solutions to proactively address a driver’s issue.

 

After this data is transformed, the Trimble model develops predictors, which are fed into a predictive engine that identifies at-risk drivers and scores risk factors. While predictions are important, it is is also crucial to develop solutions to help remedy the situation. The Trimble driver retention platform includes a prescriptive engine that provides a fleet with actions to help keep a driver. For example, a fleet can proactively address a driver who may be frustrated about home time or has an issue with payroll before it has the potential to cause a driver to leave.

 

Driver retention is just the start

Driver retention is only one of the many ways our customers are using machine learning to drive efficiencies and productivity. Check out our free whitepaper to learn about this technology in more detail and find out how to apply its benefits to your organization.

Ready to address driver retention in your fleet? Contact us today to see how Trimble’s solutions can help you make informed decisions to keep your drivers be safe, productive and happy.

More Blog posts

New PeopleNet Whitepaper Highlights Cybersecurity Best Practices for Fleets

Case Study: Midnite Express Stays Ahead of 3G Network Sunset by Upgrading to 4G LTE

Top 8 Reasons to Attend the in.sight User Conference // Expo

Training Your Team is Critical for a Successful ELD Implementation

Will Congress Delay the ELD Compliance Date?

FMCSA Issues “New & Improved” Guidance on Personal Conveyance Operating Status

Top Reasons to Attend the 2015 PeopleNet User Conference

Discover How Vehicle Maintenance is Transformed Through Machine Learning

A Primer on the Canadian ELD Rule

© 2019 All Rights Reserved

Privacy Policy

© 2019 All Rights Reserved

Privacy Policy