The GNY Historical Accuracy- 30 Days Chart is a historical record of how the Range Report’s machine learning-driven forecasts for the asset’s high/low volatility price bands, relative value, and trading opportunity zones fared versus the asset’s actual price moves over a span of 30 days.
Accompanying the chart is a 7-day table that details the actual high and actual low prices reached by the asset during the previous 7 days, plus what our predicted opportunity zones were for each day of the same period.
The table also includes the MAPE % that our forecasts attained during the previous 7 days, on a day by day basis. The MAPE %, also known as the mean absolute percentage error, is a statistical measure of the prediction accuracy of a forecasting method. It represents the average of the absolute percentage errors of each entry in a dataset to calculate how accurate the forecasted figures were in comparison with the actual figures. The lower MAPE %, the better a model is able to forecast values.
MAPE was selected by the GNY team as a measure of prediction accuracy as it is a straightforward metric, with, for instance, a 5% MAPE representing the average deviation between the forecasted value and the actual value of 5%, regardless of whether the deviation was positive or negative. Our MAPE % calculation takes into account our daily predicted opportunity zones for the asset and the actual high and actual low prices the asset subsequently reached.
The formula used to calculate MAPE is as follows: MAPE = (1/n) * Σ(|actual – forecast| / |actual|) * 100
The GNY accuracy rating for the last 7 days is listed beneath the 7-day table. This accuracy rating was arrived at by taking the mean absolute percentage error readings for the previous 7 days, averaging them, and then subtracting that average from 100% to provide an easy-to-understand rolling accuracy score.