Multifractal-State-Augmented Machine Learning for One-Trading-Day-Ahead USD/KRW Absolute-Return Forecasting
Fractal and Fractional · 15.09.2026 · 10 (9) · 643
DOI: 10.3390/fractalfract10090643 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fractal and Fractional, online erschienen am 15.09.2026. Verfasst von Dongxue Wang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the 2025 Annual Scientific Research Project of Kashgar University, the 2026 Annual School-Level Project of Kashgar University, the 2026 Annual Education and Teaching Reform Project of Kashgar University.
Abstract (Originalsprache)
Daily exchange-rate returns show weak average persistence, yet their multiscale organization may inform future movement magnitude. This study evaluates whether time-varying multifractal states improve one-trading-day-ahead forecasts of USD/KRW absolute returns. The raw dataset contains 6520 Federal Reserve H.10 observations from 1999 to 2024. After initialization of the 252-day rolling MFDFA window, 6268 feature-aligned observations remain for model estimation and evaluation. Seven scaling features augment Extra Trees, and forecasts are routed through pre-test terciles of singularity-spectrum width. Shuffled, phase-randomized, and IAAFT surrogates, matched-feature ablations, temporal-shift placebos, specification variants, and expanding-window thresholds assess robustness. In the locked 2020–2024 test of 1249 observations, the routed model yields an RMSE of 0.367 and an MAE of 0.271, improving on market-only Extra Trees by 1.627% and 2.245%, respectively. Temporal displacement produces upper-tail p-values of 0.020 for RMSE and 0.010 for MAE. The model’s R2 is 0.045 and its forecast–realization correlation is 0.218. Validation-calibrated 95% and 99% bands reduce interval scores by 2.160% and 5.730%, although coverage remains below nominal. External-currency gains are mixed and do not survive multiplicity adjustment. The results indicate modest, time-aligned, USD/KRW-specific predictive information; they do not establish universal transferability, causal effects, directional prediction, or trading profitability.
Förderung
- the 2025 Annual Scientific Research Project of Kashgar University
- the 2026 Annual School-Level Project of Kashgar University
- the 2026 Annual Education and Teaching Reform Project of Kashgar University
Zitieren
APA
Wang, D., & He, Y. (2026). Multifractal-State-Augmented Machine Learning for One-Trading-Day-Ahead USD/KRW Absolute-Return Forecasting. Fractal and Fractional, 10(9), 643. https://doi.org/10.3390/fractalfract10090643
Vancouver
Wang D, He Y. Multifractal-State-Augmented Machine Learning for One-Trading-Day-Ahead USD/KRW Absolute-Return Forecasting. Fractal and Fractional. 2026;10(9):643. doi:10.3390/fractalfract10090643
BibTeX
@article{Wang2026,
author = {Wang, Dongxue and He, Yugang},
title = {Multifractal-State-Augmented Machine Learning for One-Trading-Day-Ahead USD/KRW Absolute-Return Forecasting},
journal = {Fractal and Fractional},
year = {2026},
volume = {10},
number = {9},
pages = {643},
doi = {10.3390/fractalfract10090643}
}
EUVIMED