Neural ARFIMA model for forecasting BRIC exchange rates with long memory

2025/09/08 by Donia Besher, Chakraborty, Tanujit, Madhurima Panja +5 · 1 citation
Economics, Econometrics and Finance · Decision Sciences · #Market Dynamics and Volatility #Stock Market Forecasting Methods #Monetary Policy and Economic Impact

paper · pdf · doi:10.48550/arxiv.2509.06697

Abstract

Exchange rate forecasting remains a challenging problem, particularly for emerging economies, where the observed time series exhibit pronounced long-memory dependence, nonlinear dynamics, and sensitivity to macro-financial drivers. Classical models such as ARFIMA capture long-range persistence but fail to adequately represent nonlinear relationships, while modern machine learning approaches often neglect the underlying long-memory structure in macroeconomic series. To address this gap, we propose a Neural AutoRegressive Fractionally Integrated Moving Average (NARFIMA) model that integrates ARFIMA-based long-memory modeling with neural networks for nonlinear function approximation, while incorporating exogenous macroeconomic and uncertainty indicators. The framework provides a unified approach for capturing persistence, nonlinear dynamics, and external shocks. We establish asymptotic stationarity of the NARFIMA process and develop conformal prediction intervals for distribution-free uncertainty quantification. Empirical results for BRIC exchange rates show that NARFIMA consistently outperforms a broad range of forecasting benchmarks across multiple horizons, underscoring the importance of explicitly modeling long-memory dependence in exchange rate dynamics. The `narfima' R package provides an implementation of our approach.

Citations

• Forecasting CPI inflation under economic policy and geopolitical uncertainties
• A nonlinearity and model specification test for functional time series
• Are Transformers Effective for Time Series Forecasting?
• Do RNN and LSTM have Long Memory?
• N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
• The BRICS—merely a fable? Emerging power alliances in global trade governance
• Monetary policy uncertainty
• DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
• Of Quantiles and Expectiles: Consistent Scoring Functions, Choquet Representations, and Forecast Rankings
• Out-of-sample exchange rate predictability with Taylor rule fundamentals
• Long Short-Term Memory
• Multilayer feedforward networks are universal approximators
• Generalized autoregressive conditional heteroskedasticity

Cited by

• Early-Warning Signals of Political Risk in Stablecoin Markets: Human and Algorithmic Behavior Around the 2024 U.S. Election
• Probabilistic Forecasting of Climate Policy Uncertainty: The Role of Macro-financial Variables and Google Search Data

Related

• Advancing Exchange Rate Forecasting: Leveraging Machine Learning and AI for Enhanced Accuracy in Global Financial Markets
• Using Recurrent Neural Networks To Forecasting of Forex
• Forecasting Commodity Prices Using Long Short-Term Memory Neural\n Networks
• Forecasting Foreign Exchange Rate: A Multivariate Comparative Analysis between Traditional Econometric, Contemporary Machine Learning & Deep Learning Techniques
• Interval Forecasts for Gas Prices in the Face of Structural Breaks -- Statistical Models vs. Neural Networks