Use your data like IndyCar!

The headline: IndyCar (and F1) race teams generate 1.5TB of data per race. Not quite the 15TB of data per lap generated in the Autonomous Racing League, but it’s still a lot of data. And they use it.

Why it matters: You can use your data like IndyCar by tapping into it when preparing for race day, monitoring performance with data, and relying on data-driven exceptions to detect a problem.

The backstory: My colleague, Soren Pal, CRCR, CRCP, and I presented to 100+ health insurance professionals a few weeks ago. He’s a Hoosier. A boilermaker. An Indianian An Indian. An IndyCar and F1 fan. A friend. He shared this great analogy to help our audience use their data like IndyCar.

First things first: That 1.5TB of data generated each race is made up of 500 billion data points. It’s captured by 300+ sensors and transmitted over 1 mile of wiring -- every second. From tire pressure to driver heart rate, the data is monitored by a 1,200+ person team while the car speeds at 230+ mph.

IndyCar uses data in three ways:

1. To prepare. They review weather data. They benchmark against other cars, just like my son's college track team. They study track and telemetry data from qualifying and make adjustments for race day.
2. To monitor. They capture real-time data (almost as much as my mom) and monitor a dashboard. Your car shows MPH, oil temp, and voltage. An IndyCar shows brake temp and more.
3. To detect. Using the data, they know when something is about to go wrong. The sensors feed into AI models that alert the team of an exception, prompting them to take action.

Use your data like IndyCar:

1. To prepare. Whether you're a health insurance actuary (who we presented to) or preparing for a marathon (as I am), use your data to prepare. Look at historic trends to refine your future plans.
2. To monitor. I monitor my pace when running. It helps me adjust my speed and follow my plan (see above). But there's more to the story. Your dashboards likely need to give you more insight.
3. To detect. You shouldn't have to monitor 300 gauges. You can define exceptions, using rules or AI, to detect and alert you of a problem -- whether it's a trend out of range or a complex data issue.

Here's why: Data is key to winning!

Alex Castrounis, former Engineer, Race Strategist, & Data Scientist said

“Competitive advantage is an outcome... Data is the critical ingredient, along with the analytical skills to turn it into greater value than your competitors. Data is key to winning consistently.”

The takeaway: After using your historic data to build a plan (then execute), monitor the real-time 'micro trends' (then adjust) and define the exception tests to detect a problem (then take action).

How to start: Analytics is accessible. It doesn't require $50K in software and a $250K/yr data scientist. I use Alteryx and Tableau to 'nerd out' on my running data. You can use Tableau Public for free or open source tools.

Final thought: Coincidentally, as Soren and I were presenting on using data-driven exception tests to detect benefit plan configuration issues, my car was in the shop. A transmission sensor detected an issue.

• Good news: it was actually the sensor that was bad -- not my transmission.
• Bad news: it was still $600 to replace the sensor.

Even with a perfect exception test, the test can break due to bad data.

This article is part of my blog, Running Thoughts on Data. My first post, The Story My Data Cannot Tell, shares the genesis of my blog. The views and postings on this site are my own and do not necessarily represent those of Plante Moran.