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 Int
The increasing sophistication of AI models and the pressing need for better foresight in volatile emerging markets are driving the development of hybrid forecasting solutions.
Improved exchange rate forecasting, especially for BRIC nations, impacts international trade, investment strategies, and the stability of global financial markets.
The blend of traditional econometric models with advanced machine learning offers a more nuanced approach to handling long-memory dependence and nonlinearities in economic time series.
- · Financial institutions in emerging markets
- · Quantitative traders
- · AI/ML model developers
- · Econometricians
- · Traditional qualitative FOREX analysts
- · Portfolio managers relying solely on linear models
More accurate predictions for BRIC economies' currency movements will emerge.
This could lead to more stable foreign direct investment and reduced capital flight risk in these nations.
Enhanced financial stability in emerging markets may further consolidate their economic power and potentially influence global reserve currency dynamics.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG