Data surfaces small insights that yield winning results

By and Jay Mason | 7 minute read | July 22, 2016

leadspace image of team usa training

Enter the data scientist

Today’s competitive coaching roles are mired with seemingly incompatible skills and responsibilities. Unique sport expertise, competitive landscape, ever-evolving training methodology, sports medicine, modern technology, not to mention organizational navigation, logistics and equipment design to name a few of the key qualifications for a successful coach. Enter the data scientist and the new world of digital coaching.

team usa listen to coachUSA Cycling team listens intently to their coach

When the coaching staff of USA Team Pursuit met with IBM jStart, we simply asked them, ‘how can we help?’. We didn’t pitch analytics, IoT or cognitive. We didn’t tell them about our technical prowess in these and other emerging technologies.  We listened. We heard them talk about the laboratory-like environment of track racing and how they can now quantify racer improvements by a maximum of three percent annually. We listened intently as they described their lack of easy visibility into performance data and the long delays they had in accessing track metrics. We heard about the hours they put in after each practice to manually comb through stop-watch reports and power meter data.  They wanted to be able to better understand in precise terms and then articulate to their athletes what a poor exchange will cost and what will be needed to make up the time. Better yet, could they provide the riders the information real time during the exchange? We got to work.

j-start graphicWe started small

Within a month, we were back with a simple user-interface actively displaying the average pull, average non-pull and the average of both. Initially, the bar charts were enabled for a single rider; power over time. At the next training camp the first version of the mobile app carried in the back pocket of the cyclist’s skin suit was tested. The objective was to show that data could be streamed from the bike power meter and stored in the cloud. jStart enhanced the app to collect the new SmO2 data from a BSX Insight device along with the first version of an iPad app interface that displayed mobile phone and sensor device status in the collection process. Over the next few months the jStart team leveraged IBM Cloud, Watson IOT and Spark services to not only provide the coaches the analytics at the end of the session, but also in real time.

team usa cycle equipmentCollecting data from Team USA

This in itself saved the coaches hours per day of manual analysis. The platform was expanded to view all riders simultaneously, thus multiplying its value. Next step, live analytics to demonstrate percentages. What is W’ (W prime)? We learned, measured and collected the data. Can you detect matches burned and provide the riders that feedback when it happens? Sure, let’s connect another device.

Perishable insight –
Information needs to be delivered
quickly in order to effect
decision making.

This was before putting it altogether on summary visualizations to make it easy to have conversations with non-technical team members and staff.  This was before we added the live-feed speed line. Wrapping it together to view it over time, the various sub-components were linked over the top of the power graph for a consolidated view of the run.

“We have a new way and a new perspective to digest and interpret data”
– Coach Andy Sparks

team usa on start lineTeam USA at the start-line

“The biggest thing is just that constant information immediately after an effort. We are doing an effort, getting feedback, changing that effort, doing the next one. So we are not getting four efforts in, in a day, and then figuring out what we did wrong or did right that night.”

– Sarah Hammer, Cyclist

team usa toe clipSetting off on a training lap

“It is really important because you can immediately correct something right there in that moment instead of doing it, figuring it was wrong, coming back and trying again. It makes our time really productive.”

– Ruth Windner, Cyclist

“Having the data, any sort of data and particularly biofeedback data and power data immediately available for us while we are either training or racing is extremely critical because so much of our sport involves being innovative and being able to change and react very quickly. So even between rounds of our races, we need to go and gauge what went right, what went wrong and make the minute adjustments that could be the difference between getting first and getting fifth.”

– Kelly Catlin, Cyclist

team usa pursuitPursuit training

“ I think all this technology really helps tailor everything to us individually. Seeing how we all react to different workouts and different environments.  Some are are more sprint based or more endurance based athletes. Our team has a combination of both. And so the recovery time between different types of efforts for various athletes is drastically different. We are able to see that and accommodate it so that we are all able to improve in our paths. We are able to improve based on different strengths and weaknesses.”

– Jennifer Valente, Cyclist

“The team works so much better having data right after an effort or a practice.
It is like you have that immediate viewing of what you need to work on.”

Chloe Dygert, Cyclist

team usa review their performance looking at dataThe team reviews their performance

We grew the solution

The two velodromes where most team training occur are equipped with timing systems that provide automated rider time capture. The velodrome is wired to gather data from the live lines on the track and transponders on the bikes  The coaches would most benefit from the split time data in real-time. They were still using stop watches because the mechanized system did not support their needs. jStart asked why use stop watches when you have a timing system?  jStart commissioned integration partner, M&S Consulting, to leverage IBM Cloud services capabilities to stream the timing data and make it real-time accessible to the jStart iPad real-time dashboard.

M&S consulting logoWith the solution from M&S Consulting, exact times for all four riders as each crosses one of four or more locations on each lap, and times are automatically fed to Watson IoT for more immediate feedback and integration with other data feeds (power, heart rate, etc.) for correlation and advanced analytics on IBM Bluemix.

team usa on start lineOn the start line ready to train

Architecting this solution led to the discovery of many parallels to IoT issues we encounter in industry. We worked hard to overcome real-world challenges such as device failure, non-standard data formats, poor data quality, and inconsistent Internet access. Perishable insight – information needs to be delivered quickly in order to effect decision making. If it takes too long, the opportunity for improving performance is lost or severely diminished. Interaction of multiple components to optimize overall system efficiency. In Women’s Team Pursuit, all of the cyclists play a critical role as their interactions on the track are carefully orchestrated. We see the same in industry, where for example, the components in a manufacturing system need to be carefully synchronized in order to exceed quality standards and optimize process yield. 1% performance boost – in the end, time is the ultimate measurement in track cycling and in business. When world-class organizations compete in the marketplace, a small improvement in process performance can yield significant benefits, especially when compounded across a series of transactions or customer interactions.

In the end, time is the

ultimate measurement

in track cycling and
in business.

We listened, some more

Initially, the coaches were the clients. Very quickly, the athletes were leaning in to view and understand their own performance analysis. Real-time feedback during an exchange became common fare. Moreover, they even changed our process. They wanted an instant text to their phones of the dashboard coverage at the end of every run. They would review it while catching their breath. What does it mean to an athlete honing their craft?

Sarah Hammer – USA Cycling Medal winning athlete talks about IBM USA Cycling Team Pursuit Solution

“Riders can really get maximum takeaway from maximizing the learning that we can have out of each effort”

– Coach Andy Sparks

We are fans

Over the months the IBM jStart Team have worked with this group of people, they have made us feel like champions. Cheering as a new functionality comes online and high-fiving when the visualization yields meaningful results. All the while, they continue to push themselves to new heights. We admire them for their tireless dedication and we wish them well as they take their places in history. When August arrives, we will be watching and cheering, as their biggest fans.

USA Cycling Women’s Team Pursuit has joined forces with Watson IoT, IBM MobileFirst, IBM Analytics and IBM jStart to incorporate real-time data analytics from the internet of things (IoT) into their training. The culmination of the passion, skill and conditioning of the cyclists and coaches, coupled with the most advanced technologies including wearables, give this team the competitive edge they need as they go for gold.

Join us each week as we explore the Team Pursuit #RidetoRio through the lens of photographer John Huet and the words of the athletes, coaches and technologists.