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

TL;DR

This paper presents a novel time-series forecasting approach using fractional differencing to better capture long-term dependencies, demonstrating improved performance over traditional methods on financial data with sentiment analysis.

Contribution

Introduces a fractional differencing-based forecasting strategy that preserves memory and enhances long-term dependency modeling in time series data.

Findings

FD outperforms integer differencing in forecasting accuracy

Superiority confirmed by ROCAUC and MCC metrics

Effective integration of sentiment analysis with FD

Abstract

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 empirical analysis explores the effectiveness of FD in conjunction with binary classification of target variables. Supervised classification algorithms were employed to validate the performance of FD series. The results demonstrate the superiority of FD over integer differencing, as confirmed by Receiver Operating Characteristic/Area Under the Curve (ROCAUC) and Mathews Correlation Coefficient (MCC) evaluations.