Minimizing driving risk in a fleet vehicle is a valuable project because accidents can significantly disrupt business operations and result in a net increase in operations costs. To promote fleet safety, fleet managers closely monitor and track fleet driving behavior. Azuga’s next-gen GPS vehicle tracking, along with its Driver Score using events detected by the OBDII device, can be influential in helping fleet managers measure safe driving and set targets using such metrics.
Azuga’s Driver Scores
Azuga’s Driver Score accounts for a contextual spatiotemporal index for each event. This means we consider whether the event occurred under high-risk conditions. For instance, when a speeding event occurs, the system considers the following factors:
- Thresholds set by the user
- Posted speed limits
- Time of the event (high, moderate, or low risk hours)
- Prevailing weather (snow or rain)
- Magnitude of the event
- Duration of the event
- Frequency of the event
These factors are known predictors of crash events.
Then, a Driver Score for each day’s driving is generated along with component scores for braking, speeding, acceleration, seatbelt use, and distracted driving. The Driver Score reflects the ‘risk’ associated with the driver during that day. It allows management to compare drivers to one another or compare the same driver across time. How does it help predict crash events?
We’ve built accident risk models using three years of accident data from large commercial fleets. This shows that hard braking, hard acceleration events, and speeding are strong predictors of accidents. Such events during high-risk and peak hours increase risk.
Azuga’s Accident Models
Azuga has obtained preventable and unpreventable accident data maintained by three large commercial fleets in the United States and Canada. We correlated this data with behavior data for each driver’s data, as captured by our OBDII devices. An analysis of summary statistics for driving behavior metrics shows that the average of these metrics is different for drivers with accidents and drivers with no recorded accidents. This discrepancy indicates that these factors could influence risk.
We developed models for time-to-event (in days) with variables including driving behavior parameters, time of day miles, the proportion of unfamiliar stretches driven, and the ratio of short trips. Of the behavioral parameters, the average number of hard braking events per 100 miles is highly significant. Speeding violations were statistically significant for some fleets. Although not statistically significant, hard acceleration events per 100 miles are directionally consistent with the expected relationship.
Our models show that for every hard braking event per 100 miles, the risk of a preventable accident increases by 20.1% (2 events increase risk by 44.1%). Similarly, speeding for 1 minute above 80 mph for every 100 miles of driving increases the risk by 7% (10 minutes of speeding for every 100 miles doubles the risk). The risk is further affected by the time of day these events occur.
Azuga’s average driver scores during this time were modeled with component scores (acceleration, braking, and speeding scores) as predictors. The model parameters for Azuga’s braking and acceleration scores are significant predictors and correspond with the event-based model. A 10-point increase in the braking, acceleration, and speeding scores decreases the risk of a preventable accident by 26.3%, 3.3%, and 24.0%, respectively. For Azuga’s overall Driver Scores, a 10-point increase reduces accident risk by 57.4%, indicating that Azuga’s Driver Scores are strong predictors of an accident.
Safety Scores: A Breakdown
When it comes down to measuring safety scores, the factors measure out to the following:
- 30% braking
- 10% speeding
- 10% acceleration
- 10% idling
- 10% cornering
- 20% distracted driving
- 10% seatbelt
*Percentages differ when particular concerns are disabled, such as seatbelts or cornering.
Learn about our driver scoring algorithm.
The risk is real. The risk is closer than it appears.
How to Use Driver Scores to Your Advantage
Why spend all this time calculating if you don’t know how to use these scores? Evaluating your drivers’ safety in a quantifiable way has a wide variety of uses.
- Driver Rewards: Driver scores are integral to Azuga’s driver rewards program. This program helps determine your team’s best driver so you can reward them with gift cards to their favorite places. Instill friendly competition within your organization while boosting your fleet’s safety.
- Training: Use driver scores as a quantifiable measure to show progress toward meeting training goals. It’s pointless to train drivers if you don’t know that the information is getting through. Track your progress and adjust your training as needed to ensure effectiveness.
- Driver Evaluation: When it comes time for annual reviews and raises, you need data to back up your decisions. Driver scores are a great piece of information to have in this circumstance. You can use driver scores to determine who’s up for a raise or to determine who needs improvement and where.
Related Resources
How Fleet Driver Scores Can Improve Safety & Productivity
August 31st, 2021
There are two areas where many fleet managers would like to see improvement: safety and productivity. Rather than attempting to force your driver to improve their driving habits, motivate them with workplace gamification.
How Azuga's Scoring Models Bring Unmatched Accuracy to Safety Assessments
September 3rd, 2021
Conducting safety assessments not only keeps your drivers safe but lowers insurance rates and helps vehicles last longer. Find out how to get safety assessment reports and how Azuga’s technology gets you started on the right foot.
How to Implement a Rewards System for Fleet Drivers
September 6th, 2021
Driver rewards programs create a culture of safety within fleets that may have previously struggled. This article will outline how to implement a safe driver rewards program successfully so you can create this safety culture as well.
