0.80\u20131.00<\/td> very strong correlation<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\nSince MacroFactor\u2019s algorithms aim to predict users\u2019 rates of weight change based on their energy intake, strong performance would coincide with a large, positive r-value. Smaller r-values would suggest that we were doing a poor job of estimating energy needs, and negative r-values would mean we were doing an extremely poor job of estimating energy needs.<\/p>\n\n\n\n
Starting with our point of comparison, formula-based TDEE estimations were able to predict monthly rates of weight change with an r-value of 0.595. This is right in between a \u201cmoderate\u201d and a \u201cstrong\u201d correlation. Not too bad!<\/p>\n\n\n\n
However, MacroFactor\u2019s weight change predictions are far<\/em> more strongly associated with users\u2019 observed rates of weight change, with a r-value of 0.869. This is comfortably a \u201cvery strong\u201d correlation. This also means that MacroFactor\u2019s equations explain more than twice as much variance in observed rates of weight change compared to predictions from TDEE formulas (r2<\/sup> = 0.755 for MacroFactor vs. r2<\/sup> = 0.354 for TDEE formulas).<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\t\n\t\t\t\n\t\t\t\tOf course, there\u2019s plenty of noise in monthly data, not to mention that each user has 70 individual data points represented in both of the graphs above (meaning that each data point isn\u2019t independent of all other data points, which is technically<\/em> not advised for simple correlation analysis). So, let\u2019s take a look at how well MacroFactor and TDEE formulas were able to predict users\u2019 total weight change over the 100-day challenge period, with one data point per user.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tThe correlation coefficients increase for both (r = 0.94 for MacroFactor vs. r = 0.61 for TDEE formulas), but now MacroFactor\u2019s predictions explain nearly 90% of the variance in observed weight change, while predictions from TDEE formulas still explain less than 40% of the variance.<\/p>\n\n\n\n
Cumulative accuracy<\/h2>\n\n\n\n Since we primarily focus on predictive validity when evaluating the performance of MacroFactor\u2019s algorithms, there\u2019s something of an upper limit on assessed<\/em> performance over any finite time scale, because short-term<\/em> weight changes don\u2019t always reflect changes in energy status.<\/p>\n\n\n\nTo illustrate, let\u2019s just assume that MacroFactor\u2019s algorithms are literally perfect (I\u2019m not saying that they are \u2014 this is purely for illustrative purposes): they perfectly track with your energy expenditure, so they can always predict the size of your cumulative energy surplus or deficit over any time scale with zero error. Over relatively long time scales, your cumulative energy surplus or deficit is<\/em> the primary determinant of weight change, but in the short term, your weight can fluctuate for reasons unrelated to energy balance. So, if you assessed how well this perfect algorithm could predict weight changes over any finite period of time, it would never<\/em> get a \u201cperfect score.\u201d<\/p>\n\n\n\nFor example, if you assess the performance of this perfect algorithm over a month, some people are going to start or end that month weighing a couple of pounds more or less than their \u201ctrue\u201d weight simply due to dehydration, low glycogen stores, bloating, constipation, etc. Observed rates of weight change will<\/em> differ \u2014 at least to some degree \u2014 from theoretically perfect predictions pegged to energy balance, just due to the inherent noise in weight data.<\/p>\n\n\n\nHowever, this apparent error due to the noisiness of weight data should<\/em> be similar on an absolute basis over basically all finite time scales. In other words, the number on the scale may change by a pound or two more than it theoretically \u201cshould\u201d due to things like water weight, bloating, glycogen stores, etc., but these apparent errors should be similar in magnitude (on average) over a week, a month, a year, or a decade. So, when you instead calculate per day<\/em> error rates, they should be expected to decrease over time. A pound of \u201cerror\u201d just resulting from the noisiness of weight data is 0.14lb of prediction error per day over the course of a week, 0.03lb of prediction error per day over the course of a month, and 0.003lb of prediction error per day over the course of a year.<\/p>\n\n\n\nSo, by assessing the behavior of cumulative per-day error rates, we can gain confidence that the algorithms are actually doing a good job of helping people achieve their desired rate of weight change over time, and we can cut through some of the inherent noisiness of that weight data.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tOverall, this is the type of pattern we like to see: per-day error consistently decreasing over time. By the end of the 100-day challenge period, the median weight change prediction error per day was only 0.031lb, with an interquartile range (IQR) of 0.014\u20130.054lb per day. In other words, if you set a goal of gaining or losing some amount of weight, and you perfectly<\/em> followed MacroFactor\u2019s recommendations for 100 days, you should generally expect your final weight to be within about 3.1lb of your goal.<\/p>\n\n\n\nBy comparison, if you continuously used a TDEE formula to estimate your energy expenditure (the process used by most other nutrition apps), instead of the per-day error rate gradually decreasing, the median per-day error rate essentially plateaus at about 0.085lb, with an IQR of 0.042\u20130.151lb per day. <\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tIn caloric terms, this suggests that the typical error over the course of a user\u2019s first 100 days with MacroFactor is about 4.4% of TDEE, or about 110 Calories per day. In other words, if your average expenditure for the first 100 days you use MacroFactor is estimated to be 2,500 Calories, you can be fairly confident that your actual average expenditure over that time span was between 2,390 and 2,610 Calories per day. Furthermore, the IQR for Caloric estimation errors covers the span of 50\u2013185 Calories per day, or 1.9\u20137.8% of TDEE. So, cumulative errors smaller<\/em> than 50 Calories per day are more common than cumulative errors exceeding 200 Calories per day.<\/p>\n\n\n\nIf you instead continuously used a TDEE formula, you could expect a median error of approximately 300 Calories per day (around 12% of TDEE), with an IQR of 135\u2013525 Calories per day (5.4\u201321.1% of TDEE). In other words, there\u2019s a less than 1-in-4 chance that your Calorie targets would be as accurate as those of a typical MacroFactor user, and a greater than 1-in-4 chance that your Calorie targets would be more than 500 Calories too high or too low per day.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tIt\u2019s also worth mentioning that around a quarter of the cumulative error for MacroFactor users during their first 100 days of using the app comes from errors in their initial<\/em> expenditure estimate (i.e., before the algorithms take over and converge on highly personalized recommendations after 3-4 weeks). Of the median error of 3.1lb over the first 100 days, approximately 0.8lb can be directly attributed to error in the initial estimates. Once the algorithms fully take over, the cumulative error is approximately 0.023lb per day, equivalent to a median Caloric estimation error of approximately 80 Calories per day, or 3.25% of TDEE. That is roughly the degree of ongoing accuracy that users can expect after their first 3-4 weeks of consistently using the app.<\/p>\n\n\n\nWithin-individual comparisons of accuracy<\/h3>\n\n\n\n All of the comparisons above paint MacroFactor\u2019s algorithms in a very favorable light, but they actually still undersell<\/em> the accuracy of MacroFactor\u2019s algorithms for each individual user.<\/p>\n\n\n\nWhen you just compare the medians and interquartile ranges seen in the graphs and text above, it might look like MacroFactor should be more accurate for around 75\u201380% of people, with TDEE formulas being more accurate for around 20\u201325%. However, in actuality, MacroFactor is more accurate for essentially<\/em> everyone.<\/p>\n\n\n\nInstead of just looking at the distribution of prediction errors for the entire cohort of users, we can instead make within-individual comparisons: for each user, how large was the absolute prediction error with MacroFactor compared with the absolute prediction error from a TDEE formula?<\/p>\n\n\n\n
Overall, prediction errors were smaller with MacroFactor for 94.1% of users, whereas prediction errors would have been smaller with a TDEE formula for just 5.9% of users. However, even that<\/em> split still undersells the accuracy of MacroFactor.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tThe 5.9% of users who would have had nominally lower prediction errors from TDEE formulas were just users that would have gotten very accurate recommendations with both methods. In this small group of people, the average difference in 100-day prediction errors was just 0.66lb in favor of TDEE formulas.<\/p>\n\n\n\n
On the flip side, the 94.1% of users who got more accurate recommendations from MacroFactor\u2019s algorithms typically got way<\/em> more accurate recommendations from MacroFactor\u2019s algorithms, compared with the recommendations that would have come from a TDEE formula. For these users, the average 100-day prediction error with MacroFactor was 7.48lb smaller than the average 100-day prediction error from TDEE formulas.<\/p>\n\n\n\nIn other words, there\u2019s a ~94% chance that MacroFactor\u2019s algorithms will predict your energy needs more accurately than a TDEE formula would over a 100-day period. Furthermore, if you happen to be in the ~6% that would get slightly more accurate recommendations from the TDEE formula, the difference between the two would be practically imperceptible (a difference in predicted weight change error of 0.66lb over 100 days is equivalent to a difference in Calorie recommendations of about 23 Calories per day). In essence, the only time that TDEE formulas \u201cwin out\u201d is when they just so happen to produce recommendations that are virtually identical to MacroFactor\u2019s recommendations.<\/p>\n\n\n\n
But, for the ~94% of people who got more accurate recommendations from MacroFactor, the benefits were typically quite large, with an average difference in weight change prediction errors of 7.48lb over 100 days. That means that, for the vast majority of people, MacroFactor\u2019s nutrition recommendations are more accurate than the recommendations of a TDEE formula by about 262 Calories per day, on average. Furthermore, the larger the difference between MacroFactor\u2019s estimate of your energy needs and a TDEE formula\u2019s estimate of your energy needs, the more likely it is that MacroFactor\u2019s estimate is considerably more accurate.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tAll in all, MacroFactor\u2019s algorithms estimate your energy needs nearly three times more accurately than estimates derived from the types of TDEE formulas that other apps solely rely on.<\/p>\n\n\n\n
Avoiding large errors<\/h2>\n\n\n\n The final thing we assess when evaluating the algorithms is their ability to ensure that everyone<\/em> can be confident in their recommendations. It\u2019s all well and good for most<\/em> users to receive accurate recommendations from the app, but we\u2019d be extremely disappointed if a sizable minority was still receiving bad recommendations.<\/p>\n\n\n\nOur metric here is simple: How frequently do the observed weight change prediction errors imply that the app\u2019s energy expenditure estimate is off by 10% or more?<\/p>\n\n\n\n
Ten percent is our benchmark for one simple reason: MacroFactor users often want to know if they should put more trust in the app\u2019s estimate of energy needs versus their smartwatch (or other wearable device).<\/p>\n\n\n\n
As we\u2019ve covered previously<\/a>, wearables are notoriously<\/em> bad at estimating energy expenditure. That\u2019s a near-unanimous finding in the scientific literature, with a systematic review<\/a> finding that wearables under- or over-estimate energy expenditure in free-living humans by at least 10% in 82% of the studies that have tackled the question.<\/p>\n\n\n\nSo, as a motivating metric to aim for, we want to be able to flip those numbers: Instead of generating errors larger<\/em> than 10% at least 82% of the time, we want MacroFactor to generate errors smaller<\/em> than 10% at least 82% of the time.<\/p>\n\n\n\nWe\u2019re doing pretty well on that front.<\/p>\n\n\n\n
When we assess errors on a rolling 30-day basis, implied expenditure estimation errors exceeding 20% of TDEE are very rare (occurring in less than 5% of user-months following the initial 3-4 weeks of calibration). A little over<\/em> three-quarters of implied monthly errors are smaller than 10% (75.9%, to be exact) after day 30, so we do still fall slightly short of our 82% goal. Furthermore, a little over 45% of implied monthly errors are smaller than 5% of TDEE.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tHowever, when we look at periods of time exceeding a month, we do reach our goal of producing errors smaller than 10% more often than wearables produce errors larger than 10%. Over 100 days, errors exceeding 20% occur less than 2% of the time, around 55% of users have cumulative errors below 5%, and nearly 84% of users have errors below 10% of TDEE.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tGeneral notes<\/h2>\n\n\n\n Although we excluded users with strong evidence of consistent partial logging from the analyses above, I thought it might still be worth showing the impact partial logging can have. As you can see in the graph below, occasional<\/em> partial logging (for example, slipping up and partially logging one day per month) isn\u2019t that<\/em> much worse than never partial logging. However, as partial logging rates exceed 5% of days, and certainly<\/em> as partial logging rates exceed 10% of days, accuracy decreases considerably.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tI should also note that all of the analyses above only<\/em> screened out people with extensive evidence of partial logging. We didn\u2019t exclude people based on their demographic characteristics (age, sex, activity levels, etc.), or for not logging every single day of eating, weighing infrequently, or occasionally having logging data that looked fairly implausible (for example, 300lb men not losing weight while logging 1,500 Calories per day).<\/p>\n\n\n\nThe purpose of this analysis wasn\u2019t<\/em> to show the theoretical upper limits of our algorithms\u2019 performance with pristine, highly curated data. The purpose was to show how well the algorithms work for a broad, representative sample of typical users, some of whom don\u2019t<\/em> always log with perfect accuracy or consistency. Even with imperfect data, the algorithms are still able to consistently generate excellent recommendations.<\/p>\n\n\n\nBut, if you are<\/em> someone who weighs everything down to the gram and never misses a day of logging, you can reasonably expect that the algorithms will be even more accurate for you than the analyses presented in this article would suggest. However, the algorithms still work very well even if you aren\u2019t overly obsessive with your logging habits, as long as you do<\/em> avoid partial logging.<\/p>\n\n\n\nTakeaways<\/h2>\n\n\n\n Since this is an article on the MacroFactor website, I\u2019m sure you expected us to conclude that our algorithms work very well. If so, your expectations were correct. The only way to measure accuracy is to measure error, so the analyses were all presented in terms of the errors the algorithms produce. The magnitude of those errors tells us two things:<\/p>\n\n\n\n
\nThe algorithms aren\u2019t<\/em> perfect. There is<\/em> still some degree of error that\u2019s not simply attributable to initial estimation errors or the inherent noisiness of weight data.<\/li>\n\n\n\nOur algorithms are quantifiably much<\/em> better than anything else on the consumer market at estimating energy expenditure (for the purpose of recommending nutrition targets to help you reach your goals).<\/li>\n<\/ol>\n\n\n\nJust to drive the second point home, here\u2019s a final head-to-head comparison of MacroFactor versus the two most popular methods of estimating energy expenditure: TDEE formulas and wearable devices. Since the only metric we have for wearables is the frequency of errors smaller than 10%, that\u2019s the metric we\u2019ll need to use for the comparison.<\/p>\n\n\n\n\n\t\t\t\n\t\t\t\tBy this metric, MacroFactor is about twice as accurate as TDEE formulas, and about 4-5 times more accurate than wearable devices. Not too shabby.<\/p>\n\n\n\n
Ultimately, we care very deeply about the quality of our algorithms, because they\u2019re at the heart of the MacroFactor experience, and they\u2019re one of the main reasons why people use and trust MacroFactor instead of some other nutrition app. Our main goal is to help our users reach their<\/em> goals, and being able to consistently provide accurate nutrition recommendations is central to that aim. That\u2019s why<\/em> we\u2019ve invested so much effort into developing our market-leading algorithms, and it\u2019s why we\u2019re still constantly researching ways to improve them even further.<\/p>\n\n\n\n
![\"Individual-level](\"https:\/\/macrofactor.com\/wp-content\/uploads\/2025\/09\/Accuracy-Images_1-scaled.png\")