At Rand McNally, we’re committed to making fleet management more efficient and effective by leveraging Practical AI techniques including approaches to intelligently process large volumes of data and deliver prioritized and actionable insights. In today’s environment, fleet managers are no longer struggling with a lack of data but rather with too much data and the challenge of knowing which information requires immediate action. Rand’s use of Practical AI addresses this problem by helping fleet managers focus on what matters most.
Practical AI refers to the use of artificial intelligence to directly improve fleet operations. Rather than speculative, complex AI that isn’t useful in daily operations, Practical AI applies machine learning to sift through fleet data, recognize patterns, and provide personalized, context-driven insights. This enables fleet managers to prioritize the most important events without becoming overwhelmed by information.
Andre Tokman, Global Head of Data Science for Rand McNally explains, “Data is only as valuable as it is actionable. The idea is to take big data and make it feel smaller and more useful—not just overwhelm our customers with more of it.”
Every day, fleet managers are flooded with data from telematics systems, safety monitoring, driver performance tracking, and more. Sorting through this information manually can be inefficient and time-consuming. Practical AI changes the game by analyzing data across all the fleets in Rand McNally’s ecosystem, identifying key patterns, and delivering insights tailored to each fleet’s specific needs.
Bill Woolsey, Safety Director at Freymiller, explains how actionable insights have become essential to their operations. “We coach our drivers directly from the SafetyDirect data, which enables us to quickly and easily separate key signals from ‘noise’ in the data. That saves us time and makes our coaching more precise and effective.”
Freymiller’s experience shows how Practical AI helps fleet managers zero in on the most important data, empowering them to make decisions quickly and effectively.
One example of Practical AI in action is automated event ranking, which uses machine learning to rank safety events based on their severity, helping fleet managers prioritize critical incidents. This is achieved through data collected from proprietary onboard ADAS systems, which provide detailed insights into safety events such as sudden braking, lane departures, and more. With automated event ranking, managers spend less time manually reviewing data and more time acting on high-priority incidents.
Hans Molin, Rand McNally’s Chief Technology Officer, elaborates: “Automated event ranking is functionality that lets fleet managers focus on what matters most, filtering out less important events so they can respond faster to the ones that could jeopardize the safety of their team members and other drivers.”
According to Rand McNally’s testing, fleets using this feature have seen up to a 70% reduction in the number of events needing review, enabling managers to focus on actionable insights instead of routine data.
While automated event ranking is one of the key tools leveraging Practical AI, it’s only the beginning. Rand McNally continues to expand its platform by using AI to deliver more advanced solutions, such as predictive maintenance insights and diagnostics reporting. These applications allow fleet managers to monitor vehicle health, predict potential issues, and streamline repairs, further enhancing operations and reducing downtime.
With unique access to data from factory-installed systems, Rand McNally’s Practical AI solutions provide a competitive edge, allowing fleet managers to stay ahead of both operational and safety challenges.
"Our solution isn’t just giving managers more data,” Tokman added. “It’s helping them act on the right data, making fleet operations more effective across the board.”