Comparative analysis of financial data differentiation techniques using LSTM neural network

TL;DR

This paper compares traditional and fractional differencing methods for preparing financial data before applying LSTM models, demonstrating that fractional methods enhance forecasting accuracy and trading profitability.

Contribution

It introduces a comprehensive empirical comparison of differencing techniques, including fractional and tempered methods, for financial time series forecasting with LSTM networks.

Findings

Fractional differencing improves forecast accuracy.

Predictions enable profitable trading strategies.

Memory-preserving techniques are effective in finance.

Abstract

We compare traditional approach of computing logarithmic returns with the fractional differencing method and its tempered extension as methods of data preparation before their usage in advanced machine learning models. Differencing parameters are estimated using multiple techniques. The empirical investigation is conducted on data from four major stock indices covering the most recent 10-year period. The set of explanatory variables is additionally extended with technical indicators. The effectiveness of the differencing methods is evaluated using both forecast error metrics and risk-adjusted return trading performance metrics. The findings suggest that fractional differentiation methods provide a suitable data transformation technique, improving the predictive model forecasting performance. Furthermore, the generated predictions appeared to be effective in constructing profitable trading strategies for both individual assets and a portfolio of stock indices. These results underline the importance of appropriate data transformation techniques in financial time series forecasting, supporting the application of memory-preserving techniques.