CCJ

June 2014

Fleet Management News & Business Info | Commercial Carrier Journal

Issue link: https://read.dmtmag.com/i/319866

Contents of this Issue

Navigation

Page 54 of 89

COMMERCIAL CARRIER JOURNAL | JUNE 2014 53 shows. The story described how Target uses not only baby reg- istration data but also purchas- ing data to direct its marketing efforts to women it believes are pregnant. The story, with "a tone that implies wrongdoing," wrote Siegel in his book, "punctuates this by alleging an anonymous story of a man discovering his teenage daughter is pregnant only by seeing Target's market- ing offers to her." In trucking, the impetus to use predictive analytics isn't to sell products, but rather to show whether a driver is about to leave the company or have an accident. As for improving safety, whether in trucking or any field, ethical concerns "are few and none," says Siegel. "There's a lot of potential to do a lot of good." But when it comes to concerns over companies using data to reveal personal problems that could affect loyalty or performance, "There are places where the world is not comfortable with that yet," he says. Perhaps the most publicized human resources applica- tion of predictive analytics involves Hewlett-Packard. In 2011, two HP scientists analyzed data on more than 330,000 company employees to measure each one's "flight risk," or chance of quitting. The intention is to help managers prevent good employ- ees from leaving. Siegel reports the program has had modest success at HP. Still, there can be problems, as he points out: "What if your score is wrong, unfairly labeling you as disloyal and blemishing your reputation?" Here the application to trucking is more direct. With turnover rates so high, predic- tive analytics could become a major tool. So far, predictive analytics' use in human resources largely has held to the high road, say Siegel and those involved with it in trucking. "We're not peering into drivers' personal lives," says Vikas Jain, general manager of FleetRisk Advisors. "We're not accessing any data the fleet doesn't already have. We are helping the driver." Still, the process can involve identifying driver stresses that are unrelated to trucking. However, no major com- plaints stemming from fleets using predictive modeling have come from members of the Owner-Operator Indepen- dent Drivers Association, says spokesman Norita Taylor. Here is a look at three vendors with varied approaches to the same problems and serving differing niches of fleets by size. They are leaders in helping fleets use data, to varying degrees with predictive modeling, to improve retention, safety or both. Load One expediter Tom Evans drives team with his wife, Tina, running a three-truck Class 8 straight truck fleet based in Mattoon, Ill. By simply doing their jobs, Load One's Stay Metrics program allows the Evanses to earn points redeemable for merchandise. MARKETED AS: Predictive analytics EMPHASIS: Safety, retention and workers comp DATA USED: Extensive trucking data, such as drivers' starting times or change in empty miles relative to fleet average TARGET CUSTOMERS: Fleets of 500-plus trucks A unit of Omnitracs, FleetRisk Advisors positions itself explic- itly as a vendor of predictive analytics, and a good one: It received the IBM Business Analytics Excellence award in the ROI Achievement category in 2013. The FleetRisk model uses a broader data set to spot patterns that can be more accurate than what fleets traditionally have predicted using more simplistic analysis, says Jain. Every fleet uses some version of "scorecarding," says Jain, "where the fleet creates a set of attributes" such as hard-braking events or violations. "They also try to make an extrapolation that if they're not performing well, they're probably at a higher risk." However, FleetRisk's analyses show insufficient correlation there. Likewise, the company has found little correlation between accident risk and related data generated by the federal Com- pliance Safety Accountability program. "What we do is gather 1,500 to 2,000 data points from fleets," says Jain. That includes not only driver performance data, but also operational data such as telemet- rics, driver start times and variances in driver schedules, pay and miles. A fleet client can check its website ac- count "to review a list of drivers most likely to have a preventable accident, voluntary turnover, or workers comp claim in the next 28 days," says the FleetRisk website. Managers typically then would hold a 15- to 20-minute reme- diation talk with each driver on that list, Jain says. "Not to address the issue necessarily, but to assure them the fleet is there to sup- FLEETRISK ADVISORS David Broyles, operations manager for Averitt Express, says the fleet has found retention to be a "byproduct" of using FleetRisk Advisors' safety module.

Articles in this issue

Archives of this issue

view archives of CCJ - June 2014