Two-Stage Hybrid Machine Learning Model for High-Frequency Intraday Bitcoin Price Prediction Based on Technical Indicators, Variational Mode Decomposition, and Support Vector Regression

Table 3

Evaluation metrics.

Abbreviation	Metric name	Metric formula
MAE	Mean absolute error
RMSE	Sum of squared error
NMRSE	Normalized root mean squared error (normalized to the standard deviation of the original data)
MAPE	Mean absolute percentage error

are the size of the data set, original data values, mean of the original data values, predicted values, and the error, respectively.