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 5

Filtered features for Boruta algorithm feature selection.

Number	Feature	Number	Feature
1	Stochastics oscillator (stoch)	15	Volatility ratio oscillator (vor)
9	Zig zag (zz)	17	Fast percent-K stochastics (fkp)
10	Momentum indicator (mom)	20	Averaged percent-D stochastics
12	MACD signal line (cds)	26	Vertical horizontal filter (vhf.hilow)
13	MACD oscillator (cdo)	29	Welles wilder’s directional movement index (adx)