SAS® in the seat? Motorcycle racer goes streaming.


motorcycle racer thinks streaming dataSome people think motorcycle racing is a sport for thrill seekers and adrenaline junkies. So you might be surprised to hear that after many years of racing, I’ve found it to be a contemplative activity more related to precision and prediction than reckless abandon.

In motorcycle racing, the driver has to make many complex decisions in fractions of a second. Riders have to continually weigh and put into context a multitude of elements coming at them from constantly changing streams of data.

Success relies on making the best predictions as you accurately analyze shifting environmental variables. What was important milliseconds ago can quickly become irrelevant. Riders have to adjust almost instantly. Select inappropriately – and you can land in big trouble, literally.

It’s high-speed, high-stakes human decision making in action. Similar, I believe, to a business that has to make vital decisions based on constantly changing streams of data.

Decisions on the track

Like organizations that rely on business rules to orchestrate operations, motorcycle racers have to incorporate four components – acceleration, traction, balance and braking – into sets of general “racing rules.” To achieve faster lap times without crashing, they have to optimize the rules’ interactions.

Riders must constantly make split-second choices. Each competitor on the track makes these same types of decisions based on other riders’ predicted and actual behaviors. For example, riders decide how to prepare for an upcoming corner based on things like the bike’s position on the track, the increase or decrease in the turn’s radius, the change in traction as the tires change temperature and degrade, and the decreasing weight of the motorcycle as it consumes fuel. In this world of millisecond decisions, the generalized rules of acceleration, traction, balance and braking are useless without the specificity of the weighted inputs.

The business case for event stream processing

Obviously, race tracks are not the only place where complex, lightning-fast decisions have to be made. Many businesses must adjust predicted outcomes in milliseconds and take action just as fast so they can avoid mistakes, produce a wildly popular new product or make a choice that could save a life.

To stay in the race, businesses have to continually adapt as new data arrives – and it’s coming faster than ever, thanks to our abundance of devices. In this age of sensors and the Internet of Things (IoT), many complex business decisions can be improved by applying high-speed analytics to data streams.

Consider these real-world examples. They illustrate how businesses can make real-time, well-informed decisions by streaming data through an event stream processing engine where it’s analyzed on the fly.

  • For intellectual property: Businesses can prevent threats by analyzing multiple – seemingly unrelated – events in a corporate network, correlating them to their source and destination.
  • In the marketplace: Businesses can increase acceptance and/or conversion rates for offers, pricing decisions and sales by analyzing real-time customer behavior.
  • In manufacturing: Analysis of streaming data from equipment can help businesses avoid, predict and prepare for unplanned downtime and production interruptions.
  • On the highway: Fleet managers can use streaming data from vehicles to optimize gas mileage, signal timely repairs in advance of breakdowns and improve occupant safety.
  • In a hospital: Streaming data could reveal that although each vital sign or equipment reading is below an alarm threshold, the cumulative effect of elevated readings across multiple components – in just the right combination – signals failure. With this information in hand, health care workers can act faster to decrease critical infection rates, speed response times to emerging conditions, and save lives.

Winning the race

Motorcycle racers process all types of changing data and put it in the context of multiple variables while continuously discarding the irrelevant and saving the important. On the track, these real-time decisions can help you avoid crashes and (perhaps) win.

For businesses, that’s equivalent to using models that adapt to a fast-changing environment and then selecting actions optimized for the desired outcomes.

With event stream processing technology, SAS helps you distinguish relevant from irrelevant data – structured and unstructured – while processing millions of events per second. The software can cleanse and correct data as it’s in motion, detect patterns of interest, adapt models to changing input streams and position you to turn insights into action. So you’ll know precisely when and how to respond in the midst of continually changing conditions.

You may not be able to put SAS Event Stream Processing on your motorcycle to help you win the race. But far beyond the track, SAS gives businesses the insight they need to steer clear of bad decisions. It gives clarity about what might happen next. And every day it helps individuals make choices that turn the world into a safer, better place.

Learn about SAS Analytics for IoT



About Author

Edward Phillips

Edward Phillips manages a team of system engineers and data scientists in the SAS Health and Life Sciences Business Unit. Phillips is a technology industry veteran who has been working with digital data since 1991. His background includes work for Claris Corporation (a subsidiary of Apple), Oracle and Internet Security Systems. Phillips came to SAS from Network General/Net Scout, a leading network performance, security and application optimization firm. Edward has spent the last ten years helping organizations understand how to apply analytics and data mining to big data. Edward is a former competitive gymnast, circus performer, and competitive motorcycle road racer. His current passions are his family, rock climbing and pondering analytics at scale while on the race track.

1 Comment

Leave A Reply

Back to Top