This guide will help you better understand the various settings that go into deciding on what fitness will you have on race day (or on the day you’re looking to reach your achievement).  The settings affect how you’ll need to train and what will be needed to achieve the outcome you are looking for.

Main Three Options

 

Target Information Section

This is the main section that determines what fitness you’ll need to reach in order to achieve the outcome of completing the race/ride:

Training Plan Create/Update You can choose whether to update the existing plan you’re on (and associate your historical training) or you can create a new plan and start over again. Date This is the target date for the race or achievement.  The further away the date is, the more likely it will be for you be able to reach the fitness needed. Max Weekly Hours This value will restrict the number of hours will be asked to train over the course of the training plan.  This will be applied when the training plan is generated. Difficulty Score You can aim to limit the amount of Difficulty you will experience in trying to perform this race.  Generally, Difficulty Scores over 150 are rare and will be challenging to complete.  Races that involve and lot of hard, repeated efforts will increase the Difficulty Score.  Increasing this number will require less fitness for you to reach and improve a race’s fitness achievability but be harder to do on race day. Carbs Per Hour You can aim to reduce the estimated carbs per hour you will burn during the race.  This setting is particularly useful for longer events where self pacing to limit the fuelling demands will be needed for success at the race.  Lowering this value, increases the fitness you will need to reach.  Increasing this value, reduces the fitness you will need but will increase the fuelling demands and intensity you’ll need to race at. Event Readiness The default value of 2 is an ideal setting for a general race preparation.  Lower values improve your durability for the race but also will require more training to be prepared.  Higher values reduce the training you’ll need to do leading into the event.  If you are unable to get to achievability for the race, increasing this value will make the fitness more achievable.  However, this will come with greater chance your performance will fade during the race.   See the help page on Event Readiness for more details. Target Weight You can adjust your targeted race weight.  Reducing your weight on race day will lower the power requirements for the race. The greater the hilliness of the race, the more a reduction in weight will affect the outcome.  Reducing your weight beyond what you can reach can make the race more achievable however achieving the target weight may come at a cost of less power than predicted. Similarly, an increase in weight may mean you plan on going to the gym and will expect to be able to produce more power.  This can end up being higher that what the system predicts on race day and may in fact improve your chances of success.  Note: the fitness signature predictions do not account for the likely reductions/increases in fitness signature from changes to your weight.  It only affects the relative power you will need to produce to replicate the efforts.

 

Weekly Availability Section

This section helps you decide on what days you will expect to be training over the course of the plan.   (If you have specific dates that need to be accounted for, use the Planner to make changes to individual days before analyzing and forecasting a race plan).  Note that any changes here are not saved to your profile until the Forecast is saved.  This allows you to try “what-if” scenarios to see what level of commitment will be required to achieve a particular outcome.

 

General Settings Section

 

Periodization Level When generating a plan, Forecast AI will use this setting to wait until you need to do the training before assigning it.  If you like to ride a lot and want to get started early, slide this to the left.  If you’d prefer to just ride easy and do Zone 2 as long as possible, slide this to the right. Polarization Level Polarized Training involves splitting your low and high intensity into a set pattern, typicall 80/20 or 4 low intensity sessions for each 1 high intensity.  Forecast AI can look to lay out a training plan that uses these ratios for you.  The greater the ratio, the greater amount of high/peak intensity XSS you’ll get prescribed which also means more days of endurance/Zone 2 training.  If you respond well to the polarized training method and like minimizing intensity days, keep this at 80/20.  But if you’re often not motivated to go many days without intensity, slide this to the left.  This increases the frequency of high intensity training days you will get prescibed but with lower high/peak XSS training targets.  Note that in order for Forecast AI to fit the training needed into your availabile schedule, the ratio may need to be decreased. For example, if you only have an hour on your high intensity day, you may not be able to accumulate enough high/peak intensity XSS to reach your training needs so you may see greater high intensity training frequency in your schedule. Recovery Demands Xert automatically balances the recovery you need based on the form for each system every day.  This ensures that you have sufficient recovery throughout your plan.  You can fine tune the amount of recovery you will get by using this slider.  Slide it right to add more recovery time or slide it left for more aggressive training.  Sliding it right can reduce the likelihood of getting a forecasted training plan that reaches the outcome you’re looking for.  Review this link for more info. XSSR Preference You can adjust the degree of difficulty for your training by adjusting this slider.  If you’re time limited but are prepared to invest in more challenging workouts to achieve your race targets, slide this to the right.  If you have the time and are the type to go deep on race day but are not motivated to go as deep on training days, slide this left.

 

 

 

Everyone is familiar with training plans.  They generally give you workouts with perhaps the goal of preparing you for a race or maybe just to “get fit”.  How fit you will be at the end of the training plan is a bit of an unknown.  Will you be ready for the demands of the race? Will you be fit enough to podium?  Will you get dropped? Will you be “fit”? Lots of unknowns.

Wouldn’t it be great if we knew what fitness it took to podium?  Finish in the top 100? Not get dropped on the club ride? Is it just about increasing my threshold power?  Maybe I need to be punchier on the climbs because that’s where I get dropped.  Maybe I need to improve my endurance so I don’t fade later in the race.  Maybe the race ends in a bunch sprint and I need more top end power. What aspect of my fitness and performance needs to improve and by how much?

Everyone that’s ever done a workout would love an answer to this, from the beginner wanting to be able to keep up on the weekend club ride to the professional that longs to be as strong as Tadej Pogacar or Mathieu van der Poel.  We all aspire to have the fitness to achieve our goals.  If only we knew what it took and have the ability train towards achieving them.

It’s now here.  It’s called Race AI.

Here at Xert, we’ve endeavoured to answer this question and solve this very complex puzzle. As you’ll appreciate after reading this post, the effort has been a major undertaking … but we’ve finally done it.

The Race AI Solution – Break Down the Problem into Steps

Like many hard problems, it’s often good to break down a hard problem into individual steps you can solve.  Then put all the steps together and you solve the problem.  If we’re trying to take Rider A and train them towards being able to perform like Rider B did during a race or ride, we have the following steps we need to solve:

1. What’s our target? We need to analyze what Rider B did during the race/ride and assess what fitness Rider A would need to reach to do the same.
2. Is the fitness level something Rider A could achieve?
3. If not, what might they need to change in order to get there?
4. Can we ultimately generate a realistic training plan?  Is there a plan that Rider A can fit within the time they have available, accounts for their unique preferences such that they can follow the program?

If we can solve each of these 4 steps, then we’ve got the basis for generating a training plan that is uniquely tailored to you.  It should help you reach these goals by accounting for your current training status, your capacity for improvement and your ability to follow the plan.

What is the Target?

Understanding and defining the target fitness and performance level the training needs to achieve is as important as anything else that we do. Is it to raise FTP, improve durability i.e. power at the end of the race, handle shorter hills better, increase top end sprinting power or all of the above but in some balance?  Getting the target (or targets even) is the most important step since if we don’t have the right targets to aim for, everything else will be wrong, even if we did all the training and never missed a workout.

So we asked ourselves: What would be the best way to define what the target needs to be?

Best answer: Use a power file from that athlete you wish to perform like.  Many athletes make their data publicly available or if not you can request them to share a ride or race you wish to be able to do and use that.  If the power file was a race winning ride for the event you’re targeting, then being able to produce similar power would be an important step towards reaching a similar outcome.  A properly chosen power file will contain all the elements of what you need to target for your fitness in order to perform at the same level.

There’s a snag though.

If the rider was bigger or smaller than you, then their power data is not likely to be well-suited.  If it was a climber’s course and they raced at 20kg less than you, performing at the same power they did won’t help you in the race.  Similarly, if the course was flat they raced at 20kg heavier than you, performing at the same watts/kg won’t work either.  Watts and watts/kg are both not exactly ideal in this scenario. To do this correctly, the data needs to be transformed from the power they performed at, at the grade they performed it at, to the power you will need to perform to get the same result.

We solved this step problem by introducing the concept of Relative Power.  Relative Power answers the question: If Rider A at 65kg is doing 400W on a 2% climb, what would Rider B at 85kg need to do?  Using Xert’s new Relative Power algorithm, we now have the ability to transform one athlete’s race winning ride, or the athlete that was first to reach the coffee stop on the group ride, or the athlete the broke the record on the hill climb challenge, or the athlete that stole your KOM on the Strava segment, or, or …  We can transform this data into what you’d need to do at your weight (or better .. the weight you aim to be on race day .. hold that thought!).  This is the Race AI solution to Step 1.

Is it achievable?

Achievability means a lot of things since many dimensions of fitness and performance may have gone into the race/ride achievement that’s now encapsulated into the transformed data we can analyze.  What are these dimensions?

1. What FTP / Threshold Power will I need to be at?
2. How much punchiness is required, i.e. High Intensity Energy?
3. Are there no, a few or many sprint efforts involved, i.e. is Peak Power a factor?
4. Are there many repeated hard efforts over the course of a long ride, i.e. increased durability is needed?
5. Are the efforts going to put a strain on glycogen levels and require more fuelling than I’m used to?
6. Will I do better by losing a few pounds for the climbing efforts in the race or will maintaining big power on flatter parts of the course be more important?

Seems like a crazy idea to try and do all this, huh?  It was until we decided to use a secret weapon: MPA analysis.  To answer all of the above.  Step 2 of Race AI repeatedly performs MPA analysis thousands of times, and finds fitness signatures that meet all these constraints.  It then determines which of these fitness signatures are within reach based on the target date and finds the one that is the most attainable.

What if it’s not achievable?

Firstly and realistically, not every race result will be achievable.  As you will soon learn as you start interacting with the system, races performed by professionals at the top of their game, are not going to be reachable by most everyone except for the small few professionals that may have the capacity to perform at the same level.  Indeed, this could be the affirmation they need to invest into their training and seek a professional career in cycling.

Secondly, it might be possible to nudge things a bit and perhaps achieve the target as a stretch target.  For example, perhaps a reduction in your target weight might make things achievable.

Race AI allows you to make a number of adjustments to see if you can reach achievability.  Check out the Race AI Guide for more details:

When we’ve completed making all the necessary adjustments and selections, we can finally move to the last step…

Is there a training plan that I can follow?

The final step is where all the analysis and adjustments get put together and where Xert’s Forecast AI takes over and looks to map out a step-by-step, day-by-day training plan that fits within all the constraints you have – availability, weekly hours, etc.  When Forecast AI finds a training plan, you will have the so-called map that you can follow that will get you from point A to point B, where point A is where you are today and point B is having the fitness to be able to perform at the level that you had set out to achieve.

XFAI is a complex optimization process and accounts for various settings and constraints you can control and adjust:

Adjustment Explanation Availability Forecast AI will look at your riding history to determine which days of the week you like to ride, starting at what time and for how long.  If you plan on doing more (or less) training in trying to reach your target fitness, you can adjust these settings before running Forecast AI. Periodization Periodization level is an advanced setting that will instruct the system as to how much training can be postponed.  For those that are looking to do the least amount of training, move this setting to the right.  For those that like to train, and don’t wish to postpone any training, move this setting to the left. Polarization Polarized Training involves doing a high-intensity session on one day and then doing endurance work / Zone 1/2 work the following days.  This follows an 80/20 pattern or 4:1 of low intensity : high intensity training sessions.  Many athletes lack the motivation to do long endurance rides.  This is a common issue and athletes simply don’t follow programs that are polarized.  They would prefer more combined low/high intensity and with greater high-intensity repetition rates: 3:1, 2:1 or even 1:1.  Adjusting the slider to the left is intended for those athletes that do better with less polarization. Recovery Some athletes due to one reason or another, may need additional rest between sessions. They can still reach higher fitness goals but may take a bit longer to do so.  Other athletes feel that they want to do a lot more when tired.  Use the Recovery Demands slider to adjust to the level you believe is best for you.  Note that it may affect your target fitness achievability. XSSR Preference How much can you suffer during a training session?  This slider helps those athletes that want to get everything done quickly and efficiently (slide it right) whereas others need to build up their pain thresholds with training and prefer longer, easier workouts (slide it more left).

Conclusion

Race AI is a remarkable accomplishment.  It has brought together many new and innovative solutions into an integrated offering.  It solves the longest-standing challenge that has faced the endurance sport community since training was created.

In recent years, adaptive training has grown in prominence within training circles.  Static training plans have become a thing of the past.  Xert’s Adaptive Training Advisor was an early adaptive training platform, providing athletes day-to-day training advice that changed and adapted to each athlete over the course of their training.  Almost a year ago, Xert announced the Forecast AI Beta Program.  Forecast AI was a bold new initiative that raised the bar on how training could be prescribed.  Before Forecast AI, athletes trained with the hopes of achieving the goals and outcomes they were looking for.  With Xert’s Forecast AI, hopes have been upgraded to predictions.  Outcome-driven training plans are now available for the first time.

In the past year, we’ve taken a lot of feedback from coaches and athletes and have made many improvements over this time. We’ve also added substantial new capabilities.  At its core, Forecast AI (XFAI) generates training plans that are outcome-driven – goals, events, races, achievements – and have the following important features:

1. Optimized and Outcome-Driven – XFAI generates a training plan using a sophisticated outcome-driven algorithm that takes you from where you are today towards the outcome you are looking for, and generates a plan to reach it.
2. Personalized and Tailored to You – It uses a deep analysis of your training history and your preferences to create a training plan that’s unique to you.
3. Highly Flexible – It fits the training program into your day-to-day availability but also enables you to do the prescribed training following structured workout or unstructured rides, both indoor and outdoor, solo or with others.
4. Adaptable – Accommodates changes based on your availability or preference adjustments as well as adjustments needed to reach your desired outcome.

Next Level Personalized, Outcome-Driven Training Plans

We set out originally to simply take the Xert Adaptive Training Advisor and have it *forecast* the training you need to perform in the upcoming week.  What would seem like a simple endeavour mushroomed into something far more complex but also far more capable and valuable to athletes.  The team discovered many aspects of training that underlie successful training plans.  It’s been an incredible learning experience and hopefully we’ve been successful in transferring what we’ve learned over to you and enabled you to reap the rewards of all of our efforts.

Making it Personal

To say there is a “best” training plan that is suitable for everyone and we can use AI methods to find this training plan is a misunderstanding of how human physiology works.  There is simply no “one size fits all” training plan.  A good coach will go to great lengths to learn about their athlete.  They need the specifics and the details in order to prescribe the training that is best suited to them.  They recognize that everyone is different and the training that’s best for you may not be the training that’s best for another athlete.  We believe to properly prescribe training requires a deep understanding of the athlete. It’s the most important step.  Here’s how Xert characterizes each individual athlete:

1. Every athlete has a unique fitness signature – Your TP, HIE and PP reflect your specific strengths and weaknesses as an athlete.
2. Every athlete is at a unique point in their training – Low, High and Peak Training Loads and Recovery Loads are based on the training you’ve been doing and the unique mix of intensities that you have performed.
3. Every athlete responds to training differently – Low, High and Peak Training Responsiveness reflect how you have responded to training in the past.
4. Every athlete has a different pattern of training – The volume, durations, days-of-the-week you normally train form a baseline weekly training pattern.
5. Every athlete has other differences and preferences:
   1. Recovery Demands – Do you prefer more or less recovery time between training sessions?  Preference may be related to previous injuries or other personal factors.
   2. Polarization Level – Do you dislike doing long endurance workouts or prefer stricter 80/20 polarized training?
   3. Degree of difficulty – Can you handle a lot of suffering or prefer easier workouts?
6. And most importantly, every athlete has a desired outcome for the investment they expect to make in following a training plan.

All these are elements that will make the training plan generated by XFAI unique to you and unlike any other program.  A great coach will spend a lot of time working with you to establish all of these elements in order to craft a training plan that is right for you.  XFAI does the same.

Making it Flexible

Flexibility in a training program is key because people like to do things in different ways.  A training plan has to be something you not only can follow but you want to follow.  A training plan that might meet an outcome objective is nice but if you don’t want to do the training, then it’s not a great plan.  We sought to use your historical data as the starting point for the training since this is the pattern of training you already do.  It’s also very important to use your historical data since the principle of progressive overload depends on this historical knowledge.

Here, you can adjust your availability for any day of the week or even adjust individual days.  Mark the day as Flex to instruct XFAI to add time in order to achieve Progressive Overload.  Mark the day as Fixed if that’s all the time you have that day throughout the plan.

An important change we made over the course of developing XFAI was the change from prescribing workouts, to prescribing workouts and outdoor rides, to eventually landing on forecasting the training you’ll need to do.  You’ll notice that every training day is either “Low Intensity” or “High Intensity”.

Low intensity training days are days where you will ride easy and avoid high intensity.  XFAI will put these in your plan either because your status is projected to be yellow (“Tired” status) that day or it plans to hold back on intensity because you don’t have enough time that day to do what’s needed and a subsequent day is better for doing the high intensity training.

High intensity training days are days where your training status is expected to be blue (“Fresh” status) and you will be expected to be rested enough to handle a high intensity workout or ride.  XFAI will show you how much intensity is needed on that day and defines this so that you can continue to progress your high and peak training loads towards the target fitness levels needed.

Recovery days are days where your training status is red (“Very tired” status) and you should be taking downtime for recovery.  Rest days are simply days that you don’t need to be training and can focus on other activities but will not affect your ability to achieve the target fitness by the target date.

How the Training Plan Gets Generated

XFAI generates a training plan and displays progress on screen.  You can watch it as it works.  For many of you that were part of the original beta, XFAI rolled forwards and backwards generating and laying out a plan, rethinking decisions along the way.  It took a long time to run.  Since then, we found ways to improve the performance and improve how it lays out the training plan.  What makes this really unique and valuable is that you can see the end result and understand how and why it made the decisions in the process of laying out the plan.  Once this process is complete, you’ll see a plan that will make sense to you and you can even confirm for yourself that it’s indeed a plan that will achieve the outcome you requested.

Unlike other AI systems that may generate a training plan but won’t show their work, XFAI lays everything out for you, letting you see and appreciate how the outcome will be reached.  This helps you have confidence in the program which in turn will provide greater motivation for you to follow and stick with it.  You don’t have to place trust in the system.  It’s all laid out and understandable.

Executing the Training Plan and Updating it Along the Way

We took flexibility and personalization one step further and made these a part of the process of following and updating the training plan as you execute the training.  Next, next, next level stuff.  Here’s what you can do on a day-to-day basis:

Choose your own workouts or activities	You can choose from a variety of workouts and activities for each foreacasted training activity. You can even auto-generate a workout that will more precisely match the needs of the training for that day. Recently, we published a new “XSS Buckets” Garmin datafield on the Connect IQ App Store.  When you install and place this datafield on your Garmin activity profile, it logs into your Xert account and fetches the forecasted training XSS values (low, high and peak) that you need to fulfill for the current day.  This provides yet another advancement in training where you can ride unstructured to achieve the same training benefit as compared to a completely structured workout – both low and high intensity workouts of any kind.
Perform the training needed and compare results	Once you upload your ride, you can compare the training XSS targets against what you achieved on your ride.  Xert will conveniently post a chart to your Strava activity that’ll make it easy to check on progress right from Strava.
Plan your week of training if you prefer	Whether you have a rigid schedule and have to plan things out in advance or you have some flexibility and can easily handle training plan changes, XFAI will work with this.  You choose when to re-analyze and re-run the Forecast AI process to update your training plan when you want, whether that’s immediately after every ride or once-a-week.
Pin your chosen workouts and activities	Workout pinning is a new concept in training and provides a way to have pre-scheduled rides as part of your training plan.  Perhaps you prefer to do the high-intensity workout on a Thursday rather than the Friday or you always do a hard club ride on Saturdays.  Simply assign the workout you wish to do on a given day or pick a similar activity to the one you plan on doing on the weekend and click the pin icon.  This tells XFAI that you are planning to do these and to work the plan around them, using their XSS as part of the plan to achieve the target outcome.
Add in other rides and activities	Sometimes you have other rides planned but would still like to do an appropriate workout on the same day.  A great example is when you commute with your bike to work. Click the + icon and add the ride to your calendar.  Use this feature to add days you go to the gym or do other activities. Note: Since the XSS you specify or choose on this planned activity gets included in reaching your goal, be sure to assign meaningful training values that represent the benefit this activity will have towards reaching your target outcome.

Once all this is done, click the Adapt button to take all this new information and XFAI will update and re-optimize the training plan for you:

How much flexibility can be accommodated?

One thing we learned in the process of developing Forecast AI is that the flexibility you have in a training plan is dependent on how tight you will be to reach the target fitness by the target date.  A plan loses its flexibility when you miss too many days, for example, and a suitable training plan can no longer be forecasted.  Simple example: if you have a week left in your plan and had targeted to reach a TP of 250 but it’s still at 230 because of all the training you’ve missed, no training plan exists that you can follow to reach your target.  A plan can be flexible .. but at some point the flexibility goes away and if you miss the required training, the target outcome can’t be reached.

Forecast AI helps you see this happening when it highlights “magenta” days on your planner and chart.  When a plan is created, future training days depend on you achieving a certain fitness level by that date.  For example, as you build your fitness, your High Training Load may start very low, perhaps quite low after a period of Base training but as you progress in the training plan, High Training Load increases towards your target fitness.  This in turn requires more High XSS to maintain the controlled, achievable progressive overload towards the target.  If at some point XFAI expects your High Training Load (or Low or Peak) to be a certain value in order for you to complete the required training and your projected training load will be less such that you can’t complete the training on that day, it’ll be marked as magenta.  Similarly, if XFAI had mapped out a high intensity day but due to the increases that are projected in high/peak training loads and recovery loads on that day, your status may be projected to go from blue to yellow or red.  Again, these days will be marked as magenta on the plan, highlighting that the plan has an issue that may need to be addressed.  Often, it may just be a matter of clicking the Adapt button.  But if the plan has become super tight, the Adapt button might not succeed in finding a plan and you’ll need to consider either changing availability or perhaps modifying your targets.

Mouse over the magenta bar to see how the training has been affected.

Checking Progress

We’ve added a new page that provides feedback on the progress you have achieved as well as the progress you will make in the training plan.  This provides a complete picture of changes to your fitness signature both past and future as well as the corresponding training loads.  Use the slider to navigate through the past and future dates.

Conclusion

Xert’s Forecast AI has set a new high-bar when it comes to planning your training.  Ultimately, the plan you will follow:

1. Has you reaching the fitness and performance you are looking for.
2. Is highly-personalized to you, your specific situation and your unique interests in training.
3. Allows you the greatest flexibility to train in ways you prefer.  This is motivating and encourages you to stick to the training.
4. Continuously adapts to your changing schedule and the progress you have made, ensuring you can stay on track as life gets in the way.

About 7 years ago, we were the first to introduce a multi-dimensional Impulse-Response Model.  We brought in Xert Strain Score, i.e. XSS and the 3 dimensional XPMC.  Since then, Xert has been helping athletes quantify their training in unique and powerful ways.

Over the course of these last 7 years, we’ve acquired quite a bit of understanding about performance and training.  We’ve come to recognize how these models represent deeper aspects of fitness that we didn’t initially realize.  We also learned about some drawbacks that needed to be addressed.  In the course of analyzing thousands and thousands of athletes and their data, we saw opportunities to improve how the system manages this data.  We then saw how we could use this new found knowledge to further optimize training prescription.

Understanding How Impulse-Response Models Work

Before we get into the details, let’s lay some groundwork for the concepts that we’ll be exploring in this universe.  Whether it’s called a Performance Management Chart (PMC), a Freshness-and-Fitness Chart or an Xert Progression Management Chart (XPMC), they all follow the foundational principles that are part of Banister’s original Impulse-Response Model for exercise and use the concepts presented below:

The 4 Main Issues with Traditional Impulse Response Models

Impulse-Response models are remarkably robust. Despite the many drawbacks highlighted below, they work astonishingly well in a great many situations, underscoring how our bodies actually adapt according to these natural mathematical principles.

1. Scores/Training Stress
   • The main challenge with every Impulse-Response model is how to quantify training loads or training stress, particularly if it’s a single-dimensional model.  Quantifying how much of the exercise should be counted towards the accumulation of training load is the biggest challenge. Many metrics have been used and proposed over the years, many based on heart-rate or average power but they often oversimplify the training stress and ultimately make the calculation of training loads less meaningful.  Despite these rougher training stress measurements, Impulse-Response models are still a foundational part of all training prescription.
2. Single Dimensional
   • All training stress isn’t the same and can affect performance in different ways.  For example, repeated sprinting for 20s has a very different effect than repeated jogging for 20s.  Sprinting for 200 metres is different that jogging for 200 metres.  Sprinting to burn 20 kilojoules is different than jogging for 20 kilojoules.  Sprinting for 10 TSS isn’t the same as jogging for 10 TSS.  Simply put, saying “sprinting” should be put in the same bucket as “jogging” is a mistake, even though both are the same activity – running.  Training intensities affect different systems in different ways so using a single dimension to measure training stress will simply never fully represent training stress.
3. Feedback needed
   • Impulse-Response models are used to predict performance but what performance are they trying to predict? What does performance mean? For many sports such as running, it’s pretty simple: you take an athlete’s performance in races.  If the athlete only has a couple of races per year though, then you might need additional tests.  For cycling, it’s a harder problem since races don’t always push the rider to perform at their very best.  Even when they do push and reach their limit during a race, a highest mean-maximal power calculation (i.e. maximum 20 minute power, for example) isn’t always in the data.  Lab testing is often needed and if the athlete is too busy racing, you may not get enough tests in to identify the pattern between training load and performance necessary for the proper application of the Impulse-Response model.
4. Form goes too high
   • A problem we’ve discovered here at Xert, is that value for Form can misrepresent that athlete’s readiness-to-train.  Let’s use a simple example to illustrate.  Say an athlete has a TL of 50 and RL of 50 and they train 50 XSS daily.  The 50 TL is essentially homeostatic, with Form returning to zero everyday.  This requires no recovery since the daily XSS is their average daily and they can do this everyday, by definition.  If one day the athlete happens to miss a day, the following day they would expect to be able to do ~100 XSS to return to homeostasis.  If they missed 2 days, ~150 XSS .. and so on.  RL continues to decrease every day.  But a single bout of 150 XSS isn’t going to bring the athlete to homeostasis, even if Form indicates it is.  The athlete will require some rest because all they have ever done is 50 XSS. 150 XSS is a big disruption to this homeostasis.  Since Form is a measure of readiness-to-train, then it can’t become too positive suggesting the athlete has extra readiness to do a lot more.  That simply isn’t true.  At some point the theory behind what’s possible in the Impulse-Response model using the regular calculation of Form will break down and misrepresent the athlete’s true Form.

How Xert Addresses the 4 Main Issues

Xert’s MPA to the Rescue

The discovery of the math behind MPA has led to more than just discovering what your FTP is and giving you fitness breakthroughs.  It’s gone far further than this and has helped shed light on how training stress and strain affect training loads and performance.  Your fitness signature is used to calculate MPA.  How close you perform to your MPA, as it changes during the course of your workout/ride, is how we calculate strain.  Unlike other measures, this isn’t some average value or value that isn’t visible in heart-rate data (since heart-rate doesn’t reflect short, very high intensity efforts, for example).  MPA allows the ability to derive strain second-by-second.  This addresses the first issue:  1. Score/Training Stress.

Your fitness signature helps quantify which proportions each fitness signature parameter contributes to the strain associated with the current effort during a ride.  With 3 parameters: Threshold Power, High Intensity Energy and Peak Power, we can determine which of the three is being affected by strain.  That is, we can take a strain value and divide it up into Low, High and Peak systems, each corresponding to Threshold Power, High Intensity Energy and Peak Power, respectively.  Here we resolve the single dimensional problem 2. Single Dimensional and use 3 dimensions instead.

Breakthroughs are fun.  But they are hard to get, sometimes almost impossible.  But you get them far more often than those times you get a new 20 minute best power for example.  You may never get a new 20 minute best power in an entire season.  Xert’s fitness breakthroughs are the foundation of how we solve 3. Feedback Needed, rather than rely on lab testing, we can rely on day-to-day maximal efforts that most athletes have within their data.  Indeed, achieving fitness breakthroughs not only informs the model on how you’ve been progressing, but they are fun, part of racing and improve your fitness all at the same time.  An interesting phenomenon that we’ve discovered in Xert is the degree to which you express an aspect of your fitness is the same as the amount of strain you apply on it.  That’s profound.

Improving Readiness-to-Train

Addressing the fourth issue above: 4. Form goes too high, requires rethinking the Impulse-Response model fundamentals.  If we are looking to use day-to-day Form as a way to assess an athlete’s readiness-to-train, i.e. establishing a Tired or Very tired training status for example, then we’ll need to prevent Form from going too high.  This is the same as preventing RL from continuously decreasing.  We should cap RL to a more realistic value.  If an athlete has a TL of say, 100 then, in principle, 100 is their homeostatic Training Load and Recovery Load should return to 100 minimum whenever an activity with 100 XSS is performed.  RL should not decline more than what is required to return to zero form after an average day.  We recently introduced this updated calculation of RL and is clearly visible on your XPMC during periods of longer time between activities.  The consequence of this change is that you won’t see consecutive, high-volume training days with positive form.  From a planning perspective, you are not likely to feel overtrained returning from a few days off following Xert’s guidance.

​

Form goes negative immediately after a big ride since Form (i.e. freshness, readiness-to-train) is capped before the ride.

Things That Live in this Multi-Dimensional Impulse-Response Space

As you might envision, managing the data from thousands of activities and examining second-by-second XSS/strain data using your fitness signature at that time, power and MPA, then subdividing each second’s strain into Low, High and Peak XSS that then feeds each into a corresponding and different Impulse-Response model, to calculate TL, RL and Form values for each system every second is a computationally challenging effort. But Xert does precisely this.  In fact, once you have all this set up and tuned for a given athlete, a whole new universe of applications and actionable information become apparent and useful, both in predicting outcomes but also in optimizing a training program.  Let’s dig into this.

Here are various aspects of training and performance many of you may be aware of that live in this multi-dimensional space:

Concept	Explanation
Fitness and Performance	Having addressed all the main drawbacks of using an Impulse-Response model, we can correlate training loads with performance far more precisely and reliably.   We define performance as what your fitness signature parameter was at a given time.  This makes sense since your fitness breakthroughs express the changes in each of your fitness signature parameters.  By going back historically, we can see where your fitness (Low, High or Peak Training Loads ) was at a given point in time and what your corresponding Threshold Power, High Intensity Energy and Peak Power were at that time and calculate how changes in your Training Loads affect each parameter.  Xert does this for you and updates this relationship with each breakthrough processed.  The results end up computing your Training Responsiveness coefficients that you see in your Profile Settings:
Low/High/Peak Training Loads	In the course of a season, you will be doing various amounts of high-intensity training and your Low, High and Peak Training Loads will vary.  Sometimes you spend more time doing base/Zone 2 and your Low Training Load goes up while High and Peak may go down, for example.  Other times, you may be doing short Zwift races perhaps, and accumulate more High and Peak Training Load and see Low Training Load decline.  How each of your Low, High and Peak Training Loads move up and down reflects the type of training you’ve been doing.  You can evaluate where your Low, High and Peak Training Loads were at various points in the season.  It becomes readily visible that those times when you were performing well at specific types of rides and events, were those times when you were well-trained for them.  Training Loads reflect what kind of riding you had been focused on and also reflect what type of riding you were good at.  These are often one and the same.
Focus and Specificity	Similar to being able to review Low, High and Peak Training Loads, you can also interpret these as a Focus with an associated Specificity.  If you’ve been preparing for a major event in the Dolomites, you’d be training using long efforts around Threshold Power and accumulating mostly Low and High Training Loads.  You’d have few training rides that increase your Peak Training Load.  From an Xert Athlete Type standpoint, your Training Loads would have a more Climber Focus, i.e. a long duration Focus as would be appropriate for longer mountainous riding.  The ratios of your Low, High and Peak Training Loads reflect your training at a particular Focus Duration and Specificity.  This helps to better interpret what the relative effect Low, High and Peak Training Loads have on your performance.
Readiness-to-Train	Each system has its own TL, RL and Form values and we can use these values to establish a readiness-to-train.  One system may have a large negative value and requires recovery whereas another might have positive form and is ready for training.  Readiness-to-train now becomes a multi-dimensional number whereby you may need recovery in one dimension whilst being able to train another.  This is a unique aspect that can be used to identify the type of training that’s appropriate at a given point in time.  For example, if your High and Peak systems have a negative form from recent high-intensity rides but your Low system is still fresh with a positive form, then you can continue to ride but at an Endurance pace.  Xert does precisely this when it comes to identifying your readiness-to-train for High/Peak intensity workouts (Fresh/blue Training Status), readiness-to-train for Low intensity only (Tired/yellow Training Status) and full recovery needed (Very tired/red Training Status).
Recovery Demands	Not everyone handles training volume equivalently.  Some can train sooner after a workout whilst others might need a bit longer to recover.  Most of this is explained by the difference in Training Loads since those with a higher Training Load can handle more training than those with lower Training Loads (this is, again, a by definition statement and physiological assessment).  Those that average higher daily training volume than others are doing more and thus recover more quickly.  But when Training Loads are the same, some may need a bit of extra time compared to others.  In Xert, the value of Form that describes the Train/Recovery boundary is something you can tweak using the Recovery Demands slider.  Sliding it right increases the Form values for all three that define a Train/Recovery boundary.  Sliding it left decreases this.  Ultimately, this governs the amount of recovery the system assigns between each training requirement in your Training Program.
Durability and Event Readiness	Recently, the concept of durability has grown in prominence as an important training metric that’s key to your performance in races.  In Xert, we use Event Readiness as a way to characterize durability – if you’re ready for a race it means that you have built up enough durability to withstand the demands of the race, i.e. the Low, High and Peak XSS you’ll be required to perform. Durability lives in these models by virtue of being the opposite of fatigue.  Being durable equates to less fatigue.  If we know the demands of an event, we can pre-compute your accumulated fatigue both after and during. To withstand and reduce your fatigue, i.e. improve your durability, you’ll need to prepare by increasing your training accordingly.  Longer, more demanding events (think greater XSS values) require more Training Load (Low, High and Peak TL) to prepare. Determining how much Low, High and Peak TL you’ll need is a matter of seeing how each TL and RL will be affected during the course of the event’s Low, High and Peak XSS accumulation.  If we presume you’ll be fully fresh at the start, we can calculate what your TL and RL  should be for each system such that you can complete the event without accumulating too much residual fatigue. For example, if Low XSS is 200 for an event, what should your Low TL be in order to be *ready* for it?  The answer depends on how ready you would like to be.  If you just want to finish, then your Event Readiness may be a higher number and you’re fine with less durability.  If you want to win and it’s a long race, you may want to improve your durability and increase your Event Readiness in order to withstand the demands as well as, if not better than your competition.  In Xert, you can configure the Event Readiness you wish to have for your event and the system will allocate the appropriate amount of training you’ll need to perform to be ready. At the 100 minute mark, this athlete requires a day of recovery at that point. Completing the race they’ll require 2.5 days of recovery. At the 100 minute mark, this athlete is still fresh and not impacted by the race demands. At the completion of the race they’ll require just 1 day of recovery.
Tapering	Similar to Durability and Event Readiness, your TL and RL values at the start of a race and the demands of the race itself, will help identify the amount of tapering needed.  For shorter events, going into the event with only a small taper might allow you to be at the top of your fitness whereas a longer, harder event might require all three systems to be fully recovered beforehand.  Note that since RL’s decline is now capped, you can over taper for an event by resting too much beforehand and end up with less than optimal fitness and freshness for the event.
Polarized Training	Polarized training is a training method often recommended by coaches and sports scientists as it has been shown to produce great results.  Polarized training means that you should follow an 80/20 rule between low intensity/high intensity training.  80% of your training (4 out of 5 workouts) should be low intensity and 20% (1 out of 5 workouts) should be high intensity. In Xert, by employing a 3 dimensional model with 3 systems, each with different time constants for TL and RL, and managing form across all three separately, we can see how some systems might need recovery while others are ready for training.  This separation is why Polarized Training is advantageous – while some systems recover, other systems can be trained so you don’t need complete rest. We use a Train/Recover Form boundary value for each system, which helps define whether the system is ready-to-train or needs recovery.  You can control this using the Recovery Demands slider. If Form is below this number, that system requires recovery.  If Form is above this number, that system can be trained.  This applies to all three systems in Xert – Low, High and Peak.  Due to how the time constants work, your Low system recovers much faster than your High and Peak systems.  Your Low system could be thought of as your endurance system so it makes sense that it can handle more and returns to ready-to-train much sooner, with your high and peak form taking longer to recover.  This conveniently allows you to do endurance/Zone 2 training since your Low system is ready for training whilst your High and Peak system are still recovering. In Xert, Polarization Level can be adjusted and training programs like Forecast AI, can use your preferred Polarization Level, to allot the appropriate amount of high-intensity training such that you will recover according to the Polarization Level you choose.  This ensures that your training isn’t just polarized but you will be doing sufficient high-intensity to fill the 80/20 or whichever Polarization Level you choose.  One of the key tenets of polarized training is that high-intensity workouts are hard and low-intensity workouts are easy and the not hard enough and not easy enough workouts should be avoided.  The natural expression of the Xert model’s time constants with your chosen Polarization Level is used to enforce this. It ensures you get an appropriate amount of high-intensity training such that you’ll recover in time to perform the next high-intensity training according to your Polarization Level.  Note that if you don’t have time available to do all of the high and peak intensity needed for this, Forecast AI will spread out the intensity reducing the Polarization Level cycle in order for you to continue to progress towards your training target.
Periodization	It’s been well established that the human body responds to high-intensity training much faster (in terms of how quickly you improve from training) as compared to low-intensity training.  This means that what you need to train to optimize outcomes changes over the course of a training program.  This change is a type of periodized training.  In the Impulse-Response models, this translates into each system’s Training Load time constant.  Those with longer time constants, take longer to buildup and those shorter time constants, can be built up sooner.  This means that your Low intensity system (defaults to 60 days) and your High/Peak systems (default to 22 days) will need training at different times during the training program.  Xert Adaptive Training Advisor implements a standard, preset 120-day Base-Build-Peak periodization method but Xert Forecast AI manages this build from low-intensity to high/peak-intensity based on the time constants you have set and your Periodization setting.  Using the existing 22-day time constant, that’s been default TL time constant for High and Peak systems many years in fact, you’ll notice from the diagram below that a 120-day program will be naturally periodized into Base Build Peak over similar phases as the one used by the Adaptive Training Advisor by virtue of this time constant.  This discovery and interpretation of the multi-dimensional system was a confirmation of how the model implements known training best practices without having to apply any arbitrary rules.

A Bit of Background on Power-to-Weight Ratio

For anyone that’s ever watched a professional cycling race or raced in Category-based races, you’re likely to be familiar with power-to-weight ratio or watts per kilogram (W/kg): take your power output and divide it by your weight in kilograms.  This is the key metric that is used today when comparing one rider’s power vs. another rider’s:

• Pogi rode this climb at 7 W/kg for 40 minutes.
• The minimum FTP for this category race is 4.5 W/kg.
• Xert Surplus Seekers Zwift Group Ride is a 2.0 – 2.5 W/kg event.

The higher W/kg you can sustain, means the stronger a rider you are.  To get better, either you need to increase your power, decrease your weight, or both.  Being lighter is said to improve your performance hence many cyclists go on weight-loss diets to try and improve this metric.  If you can maintain your power but lose weight, your W/kg goes up making you a faster rider.  At least that’s what most people think.

However, many sports scientists have argued that W/kg is a great way to compare climbing ability, but the metric isn’t as useful on flat terrain.  Bigger riders have an advantage over smaller riders when it comes to riding on flat roads.  In fact, on a downhill section of road being heavier is better than being lighter.  Bigger riders descend faster than smaller riders. The notion that W/kg isn’t as effective for rider comparisons on flatter terrain has been well known for many years by those that have studied the sport.  Raw power on flatter terrain is better than W/kg whereas W/kg is better than raw power on steeper gradients.

Recently Published Research

Recently, research was published on using a new formula to better assess athletes called Compound Score. The research paper can be found here.  The formula is pretty simple as it takes an athlete’s W/kg and multiplies it by watts:

This simple formula is used to better compare the performance of one athlete vs. another over mixed terrain.  The research shows that overall this does better than using W/kg in predicting which athletes will perform better.  However, if the race is a mountain stage and the majority of the race is steep climbing, using W/kg is still better than using Compound Score.

Going One Step Further – Laying a New Foundation

What’s abundantly clear is that any real valuable comparison metric must take into account the gradient that will be used for the comparison and not just power and weight: the steeper it is, the more W/kg matters.  The flatter it is, the more watts matters.  To best illustrate this, we’re going to do a bit of math to help you understand what these all mean:

which is essentially 

Note the exponent shown in the above formulas.  We’ll call this exponent the Kilogram Exponent or KGE.  It is the exponent that’s applied to the weight in the denominator.  What’s clear is that KGE depends on the terrain and the gradient that is used for comparison.  The steeper the gradient, the closer to 1 it should be and the flatter the terrain, the lower the number needs to be.  At Xert, we went through the trouble to estimate the relationship between gradient and KGE using a physical model and generalized CdA and rolling resistance values based on weight:

Reading this graph, you’ll note some key points along the curve.  On flat terrain, the KGE is 0.4.  This means that weight has less than half the impact that it has at 10% where KGE is 1.  At -2.2%, weight has no bearing at all and KGE is 0.  Where KGE is 0.5, i.e. the Compound Score, is where terrain is mostly flat, averaging under 1%.  At this gradient, the effect of your weight is 50% that of W/kg.

Ok. So what does this all have to do with the price of bananas?

Using Xert Relative Power we can now solve a series of problems that has faced the cycling community when comparing data from one cyclist to another:

1. Who’s likely to be faster for a given power output between Rider A at X kg and Rider B at Y kg? If we know the grade, we can estimate.
2. How much power does Rider A at X kg need to produce to keep up with Rider B at Y kg? Again, if we know the grade, we can estimate.
3. Who is the race course best suited for?  If we take an average over time (not distance!) of the KGE, we can estimate what the requirement will be for the course and which athlete, A or B, is better suited.  That’s pretty valuable for an athlete deciding on which event to target or for a team to select the appropriate riders for events.
4. If Rider A and B are riding side-by-side and A is having to put out more relative power than Rider B, then Rider B is more efficient. Relative power can help us assess which of the two is more efficient, either due to better drafting, riding position, clothing, rolling resistance, bike CdA, drivetrain efficiency or some combination.  If we keep everything constant except for better drafting. for example, we can estimate the wattage differences due to how well a rider manages their power during a race.  That’s a pretty valuable way to assess a rider’s racecraft in staying in the draft compared to another. You could do the same analysis looking for differences in bike aerodynamics or rolling resistance, for example.  Anytime you need to compare power data from two or more riders and you want to extract something meaningful in the data, using relative power can help in that assessment whereas power or w/kg may give you misleading results.

How We Calculate Xert Relative Power

Applying relative power generally using the formulas above is quite tricky, however.  As you’re probably already thinking, what does a KGE of 0.4 on flat terrain mean?  That’s:

This is some number that is less than using just watts but more than using watts/kg:  A 70kg rider doing 200 watts on flat ground has a value of 200 / 70^0.4 = 36.6.  The value 36.6 isn’t at all intuitive.  To solve this problem, we go another step to make Xert Relative Power (XRP) something more tangible: we use a 75 kg athlete as the base weight and use the following formula.

Xert Relative Power:

This value is always in watts and translates to the power a 75 kg rider would have to produce to ride beside another rider weighing X kgs.  Here’s an example.  For a 85 kg rider doing 300W on a 2.5% grade, where the KGE = 0.7, their Xert Relative Power is:

What this means is that when an 85 kg rider is doing 300 watts on a 2.5% gradient, a 75 kg rider would have to do 275 watts to ride with them, all else equal.

Evaluating A Course for Rider Suitability using XRP

You can compare athletes for suitability for a particular course by evaluating their signature, weight, the course Focus and the course overall KGE.   Let’s use an example to illustrate.

Here are two riders for a course that favours 4 minute power (Puncheur in Xert) with an overall average grade of 2.5%, i.e. average KGE = 0.7:

In this example, the heavier rider with the higher 4 minute power has an advantage of about 13 watts over the lighter rider on this course as well as a small advantage in FTP, even though with average grade of 2.5 (KGE of 0.7), this is a fairly hilly course and would likely initially be perceived as favouring the lighter rider with the higher FTP in W/kg.

Where is Xert Relative Power Used on the Xert Platform?

There are three main applications of XRP in Xert:

1. XRP is used in Group Ride Analysis.  You can compare the data between two riders of different weights that rode together on a group ride. Xert will take into account the gradient (thus the KGE) second-by-second in the ride to calculate the XRP for every rider in the group and allow you to compare them to one another.
2. XRP is used in Race AI to transform the power from a data file that another rider performed to what the power would need to be for you at X kilograms body weight.  This enables you to understand what the demands are for the race or event at your given body weight.
3. XRP is displayed on our Xert Dashboard Garmin Datafield (coming soon!) as a rolling average.  This allows you to compare your power data with another directly, accounting for differences in weight and gradient.

XRP in Group Ride Analysis

When you complete a group ride with other Xert users and your data is shared, you can compare your average XRP for any part of the ride where you rode together.  This comparison can help you understand one or more of the following:

1. Who pulled more? XRP could be higher for those that pulled more and did more work at the front than other riders.  Maybe point that out and offer a compliment.
2. Who didn’t pull enough?  XRP could be lower for those that stayed in the pack more than others.  In a race, this is a good thing.
3. Is my power meter acting up?  If your power data is significantly different than others and you feel you rode no differently than they did, it could mean your power meter isn’t properly calibrated and/or could be inaccurate.  If you get a breakthrough and didn’t feel like you worked that hard, a quick inspection of your XRP as compared to others might reveal that your power meter data isn’t accurate.
4. That new aero bike in the group is fast! If someone in the group has lower XRP data compared to you than they did before, it could be that new aero bike or wheels or kit they have.  Maybe another in the group had a flappy jacket on and their numbers were considerably higher.  (Keep that to yourself and just make sure to give them kudos and comment on how strong they rode.)

XRP in Race AI

XRP is a key component of the Race AI feature where you can use data from other riders to assess your ability to produce similar XRP based on a comparison of their weight and the course terrain and your goal weight.  There are some key things to keep in mind when you consider what Xert is doing when computing your power requirements:

1. If the terrain is mountainous, a reduction in your target weight is going to have a significant impact on the power you will need to produce.
2. If the terrain is flat, a reduction in target weight will not affect the power requirements as much.
3. A reduction in body weight can impact your signature.  Dieting can reduce muscle mass and thus lower your fitness signature.  Depending on the course profile and how the race will be performed will provide feedback as to whether weight loss may or may not be advantageous.

Race AI Example 1	Race AI Example 2
The chart above shows the power requirements and associated MPA for the La Marmotte Alps for a cyclist that weighs 70kg.  The signature needed to complete the race within the given constraints is almost exactly the same as their current fitness signature. The average power (under More Details button) is 222 watts for this event.	But with an increase in weight of 8kgs (18 lbs) to 78 kg, this has a significant increase in relative power and thus the raw power needed.  The same goals become very challenging if not impossible given the weekly time commitment.  The average power increased 21 watts to 243 watts.

XRP on the Xert Dashboard Garmin Datafield in Real-Time

Having XRP displayed in real-time is useful in enabling a variety of capabilities that are more difficult to do with power data alone:

1. If you’ve ever asked the person beside you how much power they are putting out in order to compare with your own, using XRP helps eliminate the differences due to weight and gradient.  You can be more assured that you’re comparing “apples-to-apples” when they give you their XRP number rather than their power number.
2. You can agree on a more even pace for a group ride.  Setting watts or W/kg targets for a group ride can lead to mismatched power on hills or flatter roads, respectively.  Using XRP instead helps even things out.
3. You can target an intensity for team tactics during a race. This can be particularly useful on flatter ground where the larger/smaller individual team members may be required to hold an intensity for tactical purposes.  XRP can be used more universally as a target for various members of the team independent of their size or the terrain.

Understanding Key Concepts – Less is More

Athletes and coaches all understand that if you can produce more power, that’s a good sign.  More power = stronger rider, as we saw in the example above where we compared the values of two riders for a particular course. But when it comes to comparing XRP  from a ride using data from two or more athletes, less power is better.  This is because less XRP compared to another rider during a ride means you are using less energy to achieve the same pace and speed as another rider.  The lower XRP means you have one or more of the following advantages:

1. You stay out of the wind better than others.
2. You have a better riding position on the bike.
3. You have a better fitting and aero kit.
4. You have a bike that’s more aero.
5. Your drive-train is more efficient.
6. You have tires with better rolling resistance.
7. You have better racing/riding skills and need less energy to maintain your speed.

If you compare raw power data, you’ll miss the impact of weight and gradient in the calculations and can misinterpret the results.  With XRP, you can examine the data more readily and infer which of these might explain the differences in power between two riders.  You can then look to address these differences.

What does it mean if my XRP is Too Low or Too High as Compared to Others?

It’s important that you gather and compare quality and accurate data first and foremost.  In addition, you should ensure that each person that’s being compared has a proper weight associated with their corresponding activity.  If your data appears to be too low compared to other riders:

1. Your weight might be set too high.  Maybe the diet has kicked in?
2. Their weight might be set too low.  They don’t realize the treats at the coffee stop are having an effect?  (Sshh.. don’t tell them.)
3. Maybe your power meter might be reading too low.  Check calibration, battery levels, L/R balance changes if using a single-side power meter.
4. Their power meter might be reading too high.
5. You spent more time at the front of the group than others.

Vice versa, if your XRP is much higher than the other riders:

1. Your weight might be set too low.  Time to lay off the pizza?
2. Their weight might be set too high.  They’re keeping secrets from you.
3. Maybe your power meter might be reading too high.  Check calibration, battery levels, L/R balance changes if using a single-side power meter.
4. Their power meters might be reading too low.
5. You spent very little time at the front of the group compared to others.

Understanding XRP in Virtual Cycling

Platforms like Zwift and Rouvy, have their own weight, gravity, aero, rolling resistance and drafting physics models and are likely to resemble the XRP modeling that we use in Xert when riders are riding in the virtual world.  You can compare a group virtual ride in Xert and you can draw similar conclusions about your racing abilities and/or equipment choices, but importantly your data won’t be skewed high or low or will have power meters errors that are detectable.  This is because they are using your power data and your weight setting to adjust your speed at every point in the ride. It’s presumed to be accurate.