I am working on a supervised learning approach to Time Series Regression, and am currently investigating fractionally differentiation (optimizing the stationarity/information tradeoff) discussed chapter 5 in Dr. Lopez de Parado's Advances in Financial Machine learning.

When I previously worked with differentiated time-series predictions or order 1, reintegrating the prediction to get an absolute price target was chosen as technique.

Now the book, nor anywhere else on the internet, makes mention of reintegrating a fractionally differentiated time series prediction in the context of Finance.

1. Am I missing something?
2. Is reintegration of predictions a commonly accepted approach?
3. How would one go about undoing the operation applied in https://github.com/hudson-and-thames/mlfinlab/blob/master/mlfinlab/features/fracdiff.py

Thanks!

I am working on a supervised learning approach to Time Series Regression, and am currently investigating fractionall differentiation (optimizing the stationarity/information tradeoff) discussed chapter 5 in Dr. Lopez de Parado's Advances in Financial Machine learning.

When I previously worked with differentiated time-series predictions of order 1, reintegrating the prediction to get an absolute price target was chosen as technique.

Now the book, nor anywhere else on the internet, makes mention of reintegrating a fractionally differentiated time series prediction in the context of Finance.

1. Am I missing something?
2. Is reintegration of predictions (returns to absolute prices) a commonly accepted approach?
3. How would one go about undoing the operation applied in https://github.com/hudson-and-thames/mlfinlab/blob/master/mlfinlab/features/fracdiff.py

Thanks!