FleetRisk Advisors helps clients reduce accident rates and driver turnover

Smarter Transportation: enhancing driver safety and satisfaction

• Instrumented: Telematics data from each driver’s electronic log book is gathered into a central data warehouse and combined with employee information from other systems.
• Interconnected: Sophisticated data models analyze the data and assess each driver for key risk factors such as miles driven, sleep opportunities and pay levels, compared to company averages.
• Intelligent: Enables predictive assessment of drivers’ fatigue and job satisfaction levels, and prompts employers to intervene – helping to reduce employee turnover and prevent accidents before they occur.

Founded in 2004, FleetRisk Advisors helps trucking and logistics organizations and commercial fleets significantly improve their performance – increasing efficiency, reducing accidents and related expenses, and decreasing employee turnover. Based in Alpharetta, Georgia, the company employs 25 people and works with some of the largest commercial vehicle operators in the US.

“Trucking and logistics is an extremely challenging and competitive industry,” explains Lauren Domnick, Predictive Modeler at FleetRisk Advisors. “To meet their customers’ needs, these companies need to be able to deliver goods reliably and on schedule, while ensuring driver safety and avoiding accidents that can cause delays, damage cargoes, and even cost lives. It can be a stressful environment to work in, and the average employee turnover rate across the industry is in excess of 100 percent per year.

“We collect data from a range of sources – including near real-time telematics data from the vehicles themselves. This is centralized in our main database and ‘modeled’ to provide insight into the most important risk factors affecting each driver.”

FleetRisk was founded on the premise that companies have access to mountains of data about their drivers and vehicles. Buried within this data are insights that can enable businesses to understand past events, forecast future events, and take action or make decisions to change those future events to their advantage.

The Inside Story: Getting There

When FleetRisk Advisors began looking for a new analytics tool to power its business, the decision quickly boiled down to two options: SAS and IBM SPSS.

“Our previous solution had come from a small vendor, and we were overly reliant on them for support,” explains Lauren Domnick. “As the business grew, we knew we wanted a more flexible, enterprise-class solution. We evaluated IBM SPSS and SAS, and we felt that SPSS was more user-friendly.”

One of the major factors in the decision for the IBM solution was the ability of SPSS Collaboration and Deployment Services to automate many aspects of the data extraction, analysis and reporting processes.

“We had an excellent week-long session with SPSS Training as part of the implementation, which really showed us how we could push the boundaries with SPSS,” comments Lauren Domnick. “Our main requirement was that importing data from our database into the models should be automatic, but the solution actually delivers so much more than that. When we saw the potential of the solution, we had no problem gaining support from across the business.”

Predictive risk assessments

The FleetRisk team uses IBM^® SPSS^® Modeler to create and analyze sophisticated data models, and build up a picture of each driver’s monthly workload. The model takes into account which vehicles they have been driving, how far they have driven, how many opportunities they have had for sleep, how much time they’ve spent at work, how much they have been paid, and many other important factors that contribute to fatigue and stress.

The solution then outputs a report for each client which scores each of their drivers between one and 100, indicating the risk of having an accident or leaving the company in the near future. The report ranks the drivers in order of risk, and provides intelligent remediation to intervene with the highest-ranked drivers to address the issues that are contributing to their high risk scores.

Automating processes

Once these monthly reports are ready, they are automatically made available to clients via a web portal. The whole process is managed and automated by IBM SPSS Collaboration and Deployment Services, which takes the data files, runs the models, and generates reports that are uploaded to the web portal,

“Before we deployed the IBM SPSS software, our analytics process was basically manual at every stage,” comments Lauren Domnick. “Even getting the data from the main database and importing it into our old modeling environment was a complex process, because there was no real integration between the two systems. The introduction of SPSS Modeler and SPSS Collaboration and Deployment Services has made a dramatic difference to our operational efficiency, and gives us much more time to actually work with the data, instead of just formatting the files.”

Each month, the IBM SPSS solution saves FleetRisk’s team approximately three days on building the models themselves, two to three days on deploying and scoring, and several hours on post-scoring processes. The time saved can be used more productively, delivering significant operational cost savings and enabling the SPSS software to deliver a rapid return on investment.

Keeping drivers safe and productive

“The benefits that SPSS provides for FleetRisk are considerable, but the real story is the results that predictive analytics enable us to deliver to our clients,” says Lauren Domnick. “Across our client-base, we’re seeing a minimum of 20 percent reduction in the overall accident rate, and an 80 percent reduction in severe accidents such as rollovers, driving off the road or rear-end collisions. By identifying the risk factors – especially those that contribute to fatigue – we help our clients to intervene before accidents happen. This helps them provide a more reliable service for their customers, protects valuable cargo, and most importantly, keeps drivers and other road-users safe.”

By analyzing drivers’ pay compared to their peers and to industry averages, and combining this with other stress factors and previous employment history, FleetRisk has helped clients improve employee satisfaction, reducing employee turnover rates by a minimum of 30 percent on average. This generated important savings on recruitment and training, which are major cost centers in the trucking and logistics industry.

Lauren Domnick concludes: “IBM SPSS software has quickly become a vital enabler for the services we deliver to our clients, providing not only the advanced modeling capabilities required to predict and mitigate driver-related risks, but also the ability to automate and parallelize the majority of the reporting process. As a result, FleetRisk Advisors is able to serve its clients more efficiently and deliver ever greater improvements in driver safety and employee satisfaction.”

About IBM Business Analytics

IBM Business Analytics software delivers actionable insights decision-makers need to achieve better business performance. IBM offers a comprehensive, unified portfolio of business intelligence, predictive and advanced analytics, financial performance and strategy management, governance, risk and compliance and analytic applications.

With IBM software, companies can spot trends, patterns and anomalies, compare “what if” scenarios, predict potential threats and opportunities, identify and manage key business risks and plan, budget and forecast resources. With these deep analytic capabilities our customers around the world can better understand, anticipate and shape business outcomes.