aiqbench analysis
This article presents a Neural ARFIMA model that successfully merges classical long-memory econometric techniques with neural networks to forecast BRIC exchange rates. By explicitly addressing the limitations of both traditional linear models and standard machine learning approaches, it offers a unified framework for capturing nonlinear dynamics in macroeconomic time series. The study provides empirical evidence on emerging market currencies while establishing theoretical guarantees like asymptotic stationarity and distribution-free uncertainty quantification via conformal prediction intervals.
Neural ARFIMA model for forecasting BRIC exchange rates with long memory
arXiv:2509.06697v3 Announce Type: replace-cross 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.
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.
Econometrics (econ.EM); Machine Learning (cs.LG); Applications (stat.AP); Machine Learning (stat.ML)
arXiv:2509.06697 [econ.EM]
(or arXiv:2509.06697v3 [econ.EM] for this version)
Full text under the publisher's open licence · 181 words
Related coverage
News
Quantum Computing Report · Jul 25, 2026
The death of humanity
Fortune · Oct 16, 2026
The hard physics and complex economics of AI’s insatiable hunger for power
SiliconANGLE · Sep 11, 2026
Large-Scale Benchmarking of Quantum Neural Network Configurations for Financial Time Series Forecasting
arXiv · Oct 9, 2026