Time-Series Forecasting: Unleashing Long-Term Dependencies with Fractionally Differenced Data

This study introduces a novel forecasting strategy that leverages the power of fractional differencing (FD) to capture both short- and long-term dependencies in time series data. Unlike traditional integer differencing methods, FD preserves memory in series while stabilizing it for modeling purposes. By applying FD to financial data from the SPY index and incorporating sentiment analysis from news reports, this study presents an empirical analysis to explore the effectiveness of FD in conjunction with the binary classification of target variables. The findings reveal the superiority of FD over integer differencing. Several accuracy metrics are reported in this study, e.g., Receiver Operating Characteristic/Area Under the Curve (ROCAUC) and Mathews Correlation Coefficient (MCC) evaluations.