FTP Testing is a Thing of the Past: Introducing AI FTP Detection

Today we're making AI FTP Detection misogynist to all TrainerRoad subscribers. AI FTP Detection lets you skip the Ramp Test and simply click a sawed-off to get your FTP.

Although the outcome is simple, AI FTP Detection was years in the making. We unromantic machine learning techniques to data from TrainerRoad’s 150,000,000 dataset of indoor and outdoor rides.

AI FTP Detection uses demographic data withal with ride files from:

• Indoor workouts with power
• Indoor workouts with only an HR monitor
• Outdoor workouts with power
• Outdoor workouts with only an HR monitor

How to Use AI FTP Detection

You can use AI FTP Detection in two ways:

1. Anywhere you see the ramp test in TrainerRoad, there’s a sawed-off to launch AI FTP Detection
2. On your profile page on TrainerRoad.com

Isn’t FTP Dead?

Rumors of FTP’s death are profoundly exaggerated, but we have come a long way from simply basing workouts off of FTP. AI FTP Detection works with Adaptive Training to unravel the tight relationship between power zones and FTP.

Instead of VO2 max stuff a strict “120%” of FTP, Adaptive Training allows your VO2max and all other zones to be personalized. It learns not only an athlete’s power curve, but moreover their repeatability in their specific zones.

The outcome is a system that takes into worth your genetic predispositions to training zones (ie: stuff really good at short anaerobic work but struggling with sustained threshold) AND how those relationships transpiration during your training plan/phase.

Before we get into how we built AI FTP Detection, we need a unenduring history of FTP on TrainerRoad.

History of FTP Testing at TrainerRoad

Waaaayyy when when TrainerRoad launched in 2011, we had two ways to get your FTP; the 20-Minute Test and the 8-Minute Test.

The 20-Minute Test was based on the testing protocol employed by Hunter Allen, laid out in the power cycling classic, Racing and Training With a Power Meter.

It had athletes perform a 20-minute all-out effort without a warmup and a 5-minute “clearing” effort to hopefully reduce anaerobic contribution to the test. It took 95% of the 20-minute effort to get an athlete’s FTP.

Although this was “good” for some athletes, it had issues.

1. Athletes had to pace their 20-minute test correctly. If they started off too nonflexible or too easy, the results could be invalid.
2. Athletes had to go “ALL OUT!” on this test to get a valid result, which was very nonflexible for many athletes.
3. The strict relationship of 95% of 20-minute power to FTP didn’t get all athletes into the weightier training zones.

The 8-Minute test was similar to the 20-Minute Test, except athletes had to well-constructed 2×8 all-out efforts. Although pacing an 8-Minute Test was easier for some athletes, it still had the same issues as the 20-Minute Test.

We needed a largest way that didn’t take pacing into worth and wasn’t so nonflexible for athletes to complete.

In comes the Ramp Test!

In 2018, TrainerRoad introduced a stepped fitness test that had athletes gradually increase their wattage until they went “ALL OUT!” and couldn’t go any longer.

We then took a percentage of the athlete’s 1-minute max power to set the FTP.

The Ramp Test was a success and:

1. It was less physically draining and increasingly palatable for athletes.
2. It was easier to understand and well-constructed without issue.
3. Had a higher adoption rate compared to the 20 and 8-Minute Tests.

Although the Ramp Test was an resurgence over the 20 and 8 Minute Tests, it still wasn’t without issue.

Our percentage of 1-minute max power on the Ramp Test worked for some athletes but not all athletes. We moreover still had a strict relationship between FTP and training zones.

We needed to get better…

And then, there was Adaptive Training!

In 2021, TrainerRoad launched Adaptive Training! We introduced Progression Levels that tapped self-ruling the relationship between FTP and Training Zones.

Fun fact: Adaptive Training started surpassing we plane had the idea of the Ramp Test.

Adaptive Training would dynamically learn an athlete’s power lines and repeatability, giving them the correct workout per training zone to make them faster!

It then continually monitors athletes’ performance and changes their training in response.

Adaptive Training considers:

• Passed workouts
• Missed workouts
• Workouts you “struggle” on
• Workouts that are “too” easy
• Sickness
• Vacation
• Time off
• Accomplishing stretch/breakthrough workouts
• Tapering for Races
• Race-specific goals
• and more…

Adaptive Training was a huge step forward in cycling training. But there was still a problem.

Testing still huuurrtt and wasn’t an enjoyable experience. Testing moreover could make people yellow-eyed and not perform to their capabilities on test day.

So we imagined a world without tests.

We’re not all masochists

There are very few athletes that truly love FTP tests. They are masochists and often weird people. ;-P

We knew we had an wondrous dataset of athletes’ unshortened cycling history (indoor and outdoor). We moreover had years of athletes performing FTP tests and then doing structured, power-based workouts directly without that FTP test.

What if we could use machine learning to snift an athlete’s FTP, combine that with Adaptive Training (to take into worth individual power zone variation), and let athletes skip the FTP test and just click a button! .

We knew this would be a big, ramified problem, so we turned to machine learning.

What is Machine Learning?

Machine learning (ML) is a subset of Artificial intelligence. We used a “supervised learning” tideway to snift FTPs.

We wanted to squint for patterns and trends in people’s training to determine their FTP on a specific date. To succeed this, the team built “features,” which are specific and measurable properties of a dataset.

Some examples of features might be:

• Age
• Gender
• Years Training
• TSS in the last 3 weeks

The team ended up testing over 130 features.

We then took a subset of our data and trained an ML model on athletes’ training history and ramp test outcomes. ML went through that dataset of indoor and outdoor rides and tried to find patterns that lead to specific FTP outcomes.

We then validated the newly trained ML model versus a larger dataset of training history and ramp tests and scored it for performance. Or, in other words, how tropical it was to predicting someone’s FTP.

We took that score and tried to modernize it. The team would build new features, train new models, and then rerun them and score the performance.

This is not a small task, as this iterative tideway took years. The secret sauce is in our unique dataset of planned vs. actuals and the specific features we wrote to describe our dataset.

We plane built ML models to create features to feed into other ML models!

This might sound simple, but it was a very nonflexible problem. We had to worry well-nigh things like overfitting, data validation, and dataset quality.

Here’s a good explanation if you want to learn increasingly well-nigh machine learning.

Note: We are lucky to have cycling data before, during, between, and without using TrainerRoad. We moreover have indoor and outdoor data. If we JUST had indoor TR rides, we’d run into issues. But we often have unshortened ride histories from athletes (or as long as they’ve recorded data).

Note to Engineers: We know there are many increasingly traps and “gotchas” in AI/ML, and this blog post in no way tries to imbricate all the things we had to watch out for.

Real-World Validation of AI FTP Detection

When we got the model to a state we were happy with, we went to early wangle for AI FTP Detection, permitting our athletes to opt-in to try the new full-length while it was in the beta minutiae phase.

Over 9 months, we had 22,000 people join AI FTP Detection early access.

During this time, the team unfurled to trammels for verism by looking at expected workout performance vs. very post-AI FTP Detection use.

We remoter iterated on our ML models until we were positive that AI FTP Detection outperformed the Ramp Test by a wide margin.

Is AI FTP Detection magic?

AI FTP Detection might seem magical, but it isn’t. It needs data to virtuously snift your FTP…and the increasingly data and the increasingly recent, the better.

For those athletes who have had a recent unravel from cycling, AI FTP Detection will get you in the right ballpark. Then Adaptive Training will take over and retread your training zones without a few workouts.

AI FTP Detection is genuinely amazing, and we recommend it to all athletes with recent data.

Wait, don’t other companies snift my FTP?

Other companies do try to tell you your FTP without a test.

A key issue with these companies’ tideway is that athletes still have to make an “all-out” effort to get well-judged results. Many times at a elapsing where athletes don’t usually perform all-out efforts (like 20 minutes).

This tideway has the same issues that I wrote well-nigh above. And what if you never do an “all-out” effort? The systems still seem you did and requite you lower training zones than you should have.

AI FTP Detection is different. It doesn’t plane need power whilom threshold to snift your FTP. Athletes can do 8 weeks of traditional “long and slow” training surpassing detection and still get an well-judged FTP!

This is some of the “magic” baked into our ML and dataset.

This ways that athletes can focus on the right training for them without having to worry well-nigh mentally and physically taxing “all-out” efforts to calibrate their training zones.

Congrats to the team!

The team has washed-up a fantastic job on this and has unfurled to make it better!

This is a big day for TrainerRoad, but I think we’ll squint when at this and see it as just the whence of the paradigm-shifting advancements coming to cycling training.

Sign up or renew now to get faster

If you’re new to TrainerRoad, go to TrainerRoad.com now to sign up and get faster!

AI FTP Detection FAQ

How is this variegated from FTP detections on other platforms?

Most other platforms estimate FTP from individual weightier efforts in your training data. Our model analyzes your training history and personal biometrics for a broader, increasingly nuanced understanding of your skills than a single effort can reveal.

Is AI FTP Detection just looking at what athletes often proceeds in FTP without each woodcut and basing the model on that?

No, we are not estimating FTP based on any static equation. AI FTP Detection uses a model trained on our data set to predict your FTP based on your unique training and biometric data.

Does AI FTP Detection consider rides that aren’t TrainerRoad workouts?

Yes. AI FTP Detection takes into worth all rides with power data—indoor or outdoor, structured or unstructured. This can include group rides, races, and plane rides on other indoor training apps synced to TrainerRoad.

Will AI FTP Detection consider unstructured outside rides as well?

Yes. AI FTP Detection takes into worth all rides with power data, whether they’re indoors or outside, structured or unstructured. This can include group rides, races, and plane rides on other indoor training apps synced to TrainerRoad.

What does AI FTP Detection squint at to snift my FTP? What types of efforts or workouts does AI FTP Detection consider?

AI FTP Detection looks at your training history and your biometrics to snift your FTP. Considering AI FTP Detection considers so much of your training data, it’s very unlikely a single type of effort or workout would substantially sway the model. For example, the model “knows” when you’re doing an easy ride and won’t misplace that for decreased fitness. You moreover don’t have to do capacitive or all-out efforts for the full-length to work. In fact, it works if you only do sweet spot or aerobic riding and never do any high-intensity intervals!

Will AI FTP Detection snift my FTP if I’ve never used TrainerRoad?

AI FTP Detection requires 10 completed indoor TrainerRoad workouts to uncork detecting your FTP. Once you reach this minimum, you don’t need to do any spare TrainerRoad workouts. By enabling RideSync, you can import rides with power data from other services and protract detecting your FTP.

Does TrainerRoad recommend I use AI FTP Detection or do an FTP test?

AI FTP Detection delivers the training benchmarks you need to progress your fitness and allows you to well-constructed a productive workout in place of testing. Considering AI FTP Detection gives you productive training stress without the unnecessary psychological and physical stress of an FTP test, we recommend using AI FTP Detection. That said, you unchangingly have the option to test!

Can I still well-constructed an FTP Test?

Of course! You can still take a Ramp Test or other FTP test whenever you like. We just don’t know why you’d want to

How often will AI FTP Detection requite me a new FTP?

Depending on your current fitness, FTP often takes several weeks to meaningfully change, so AI FTP Detection often won’t snift a new FTP increasingly often than this. For now, this is why AI FTP Detection isn’t misogynist increasingly often than every 28 days.

What if my Skills Transpiration Within 28 Days?

FTP is not the only measure of your fitness. Between AI FTP Detections, your Progression Levels monitor your progress and track subtle changes in your skills from day to day, plane when your FTP doesn’t meaningfully change.

Progression Levels track your topics to express your current FTP in variegated training zones at any given time. For example, increasing your worthiness to hold steady power within your VO2 Max training zone from one minute to three minutes at the same FTP demonstrates significant progress and is reflected by changes in your Progression Levels.

Simply put, your skills will transpiration between AI FTP Detections in ways FTP vacated can’t virtuously reflect. Progression Levels have you covered, working hand-in-hand with AI FTP Detection to track every transpiration in your fitness, whether big or small, up or down.

I Didn’t Winnow my Recent AI FTP Detection. Can I Get a New Detection Sooner Than 28 Days?

If you alimony your current FTP instead of unsuspicious AI FTP Detection’s results, the newly-detected FTP will still be misogynist for you to winnow at any time during the next 28 days. Simply click the AI FTP Sawed-off from your Worth Settings or from any FTP Test, and you’ll then be presented with the option to winnow it, withal with a warm-up to when your next detection will be available.

If you haven’t wonted your newly detected FTP and something happens to significantly subtract your fitness within 28 days (for example, if you take extended time off the bike), AI FTP Detection will automatically retread your still-available prediction downwards to make sure you get the right workouts and power targets. This will prevent you from unsuspicious a too-high FTP, and it won’t stupefy the 28-day warm-up until your next detection is available.

Does AI FTP Detection predict my hour power or expected Ramp Test result?

AI FTP Detection isn’t meant to predict the results of any individual effort, considering all-out efforts can be unauthentic by nutrition, fatigue, and other subjective factors. Instead, it’s designed to requite you a training benchmark (FTP) that represents the full telescopic of your abilities, so you get the most productive training possible.

Isn’t AI FTP Detection just making training easier, and is that not the point of training?

A typical FTP test requires an all-out effort, but due to short durations and upper resulting fatigue, these tests don’t often contribute as much useful training stress as a productive workout. AI FTP Detection lets you replace your FTP test with a salubrious workout and stave a stressful, less productive effort.

How can AI FTP Detection be well-judged if I’m coming when from an offseason or increasingly than one week off the bike?

AI FTP Detection was trained on an enormous data set and can predict decreases in FTP plane without long (weeks to months) training interruptions.

How Do I Know AI FTP Detection is Accurate?

The machine learning model powering AI FTP Detection was trained on a dataset with increasingly than 150 million workouts and hundreds of thousands of FTP changes, including athletes of all variegated ages, abilities, and wits levels. But the weightier way to validate AI FTP Detection’s verism is to try it for yourself! Winnow your detected FTP and try some productive workouts. We think you’ll be amazed at the results.