Overdrive Magazine | Trucking Business News & Owner Operator Info
Issue link: http://read.dmtmag.com/i/339482
40 | Overdrive | July 2014 carriers' crystal ball he's unaware of actual litiga- tion based strictly on predic- tive modeling practices. Still, there has been controversy, says Eric Siegel, founder of the Predictive Analytics World conference series and author of "Predictive Analytics." His book explains how retailing, with marketers on a never-ending quest to pinpoint the best customers, is one major area for using predictive analytics. In trucking, though, the focus isn't on buyers, but drivers – namely, which ones are about to leave the compa- ny or have an accident. As for improving safety, whether in trucking or any field, ethical concerns "are few and none," Siegel says. But when it comes to concerns over companies using data to reveal personal attributes or problems that could affect loyalty or performance, "there are places where the world is not comfort- able with that yet," he says. Perhaps the most publicized human resources application of predictive analytics involves Hewlett-Packard. In 2011, two HP scientists analyzed data on all of more than 330,000 company employees to mea- sure each one's "flight risk," or chance of quitting. The intention is to help managers prevent good employees 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 PSP V I O LA T I ONS M il es pe r m on t h W ea t h e r HARD BR AK I NG T ra ffi c SA T I SFACT I ON SURVEY S SAFETY Q U IZ SCORES I d li ng % M A I NTENANCE R EPOR TS ON T I M E Log v i o l ations K n o w l edg e o f co m p an y g oa l s SAFETY QU I Z SCORES N on - d ri v i ng du t y h ou rs Idling % I N FRA STR UCTURE I NV EST M EN TS O n -ti m e p e rf o r m an ce Tolls 329,463 8% $ ¢ ACD FG .0044 c r ¢ 121 $ DANGER! DANGER! Identify individuals whose performance puts them at risk DETERMINE HOW KEY PATTERNS CORRELATE WITH SAFETY AND TURNOVER Crunch thousands of data points Discuss concerns with those drivers Carriers have long used safety records to weed out bad drivers. However, with predictive analytics, they use much broader data for more precise predictions, enabling them to head off potential accidents. These predictive models also can reduce turnover by opening conversations with unhappy drivers before they leave. HERE'S HOW IT WORKS: Step 1 Step 2 Step 3 Step 4 DEVISE PLAN TO REMEDIATE 1 2 3 4 5 How fleets use predictive models to avoid problems Kenneth Stubbs Predictive_Analytics_0714.indd 40 6/27/14 3:39 PM