Mean Absolute Percentage Error Calculator
Calculates average absolute forecast error as a percentage of the actual values. The form displays mean(|actual−forecast|/|actual|)×100 beside mean absolute percentage error, using a worked condition that can be recalculated with the labeled inputs.
Set the model inputs in this example
Mean absolute percentage error
What mean absolute percentage error answers
The mean absolute percentage error page calculates average absolute forecast error as a percentage of the actual values.
Mean absolute percentage error is limited to the statistical quantity named by the result panel. The mean absolute percentage error calculation does not silently add a population, time horizon, causal direction, or decision threshold that is absent from the fields.
How the inputs shape mean absolute percentage error
- Actual values: For mean absolute percentage error, the displayed actual values sequence is 12, 15, 18, 21, 24, 27. Preserve actual values order when mean absolute percentage error depends on pairing, lag, rank, or time position, and distinguish an observed zero from a missing actual values entry.
- Forecast values: For mean absolute percentage error, the displayed forecast values sequence is 13, 14, 19, 20, 25, 26. Preserve forecast values order when mean absolute percentage error depends on pairing, lag, rank, or time position, and distinguish an observed zero from a missing forecast values entry.
The entries used for mean absolute percentage error must refer to one coherent analysis condition. Combining incompatible populations, periods, or measurement definitions can produce valid mean absolute percentage error arithmetic for a nonexistent study.
How mean absolute percentage error is calculated
For mean absolute percentage error, match every symbol in the relationship to a labeled field before substituting numbers. Mean absolute percentage error is reported in %.
While checking mean absolute percentage error, use actual values observations from one defined analysis set rather than totals copied from incompatible groups.
Worked values for mean absolute percentage error
The default mean absolute percentage error condition is Actual values = 12, 15, 18, 21, 24, 27, Forecast values = 13, 14, 19, 20, 25, 26.
The example MAPE is approximately 5.5313%.
The live calculator reports MAPE 5.5313051 %. Repeating one intermediate step from mean(|actual−forecast|/|actual|)×100 provides a fixed mean absolute percentage error reference check for later code changes.
Statistical context for mean absolute percentage error
MAPE is undefined for zero actuals and can overweight small denominators.
For mean absolute percentage error, time order is part of the data. For mean absolute percentage error, reordering observations, changing the forecast origin, or mixing incomplete seasonal cycles changes the statistical question.
A nearby method may answer the next question: mean absolute scaled error, symmetric mean absolute percentage error, and autocovariance.
Putting mean absolute percentage error beside the study design
When interpreting mean absolute percentage error, keep the lag, window, seasonal period, initialization rule, and forecast horizon with the result so a later calculation uses the same timeline.
As a second check for mean absolute percentage error, outliers, ties, ordering, and missing entries can affect mean absolute percentage error even when the number of observations stays unchanged.
Input and rounding traps
Before accepting mean absolute percentage error, compare every entered value with its label, unit, and allowed domain after reading the printed relationship from left to right.
For mean absolute percentage error, do not substitute zero for an unobserved value; missingness and a measured zero describe different data.
Another mean absolute percentage error failure occurs when a rounded output is reused as though it were the original measurement. Carry guard digits through calculations that depend on mean absolute percentage error, then round only the reported value.
Reporting mean absolute percentage error reproducibly
Report mean absolute percentage error using mean(|actual−forecast|/|actual|)×100, followed by the entered values, units, exclusions, and analysis date. Name the mean absolute percentage error population or dataset boundary instead of leaving it implicit.
Keep the full calculator output with the record, including MAPE 5.5313051 %. A later mean absolute percentage error review can then distinguish a changed input from a different convention or software implementation.
Questions about mean absolute percentage error
What should be saved with mean absolute percentage error?
Save the entered values and units for actual values, forecast values, along with the analysis date, exclusions, software or formula version, and the relationship mean(|actual−forecast|/|actual|)×100. That record is sufficient to rebuild this specific mean absolute percentage error calculation.
Does mean absolute percentage error establish a causal or population conclusion?
No. The displayed mean absolute percentage error value is conditional on the entered data and named method. The mean absolute percentage error design, measurement process, and assumptions determine what can be concluded beyond those values.
How should mean absolute percentage error be rounded?
Keep the unrounded mean absolute percentage error for subsequent arithmetic, then report only the precision supported by the source measurements and the decision context. Extra digits in mean absolute percentage error do not correct sampling or model error.