Indicators: Fixed-Width Fractional Differencing (FFD)

 

Fixed-Width Fractional Differencing (FFD):

MQL5 implementation of the fixed-width fractional differencing (FFD) method from López de Prado's Advances in Financial Machine Learning (Chapter 5). Transforms a non-stationary price series into a stationary one while preserving maximum historical memory; output cross-validates against the Python afml library to within 1e-12.

Fixed-Width Fractional Differencing (FFD)

Author: Patrick Murimi Njoroge