EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Hybrid Forex Trading: Integrating Fuzzy Price Action with AutoML

Saim Anwar, Haider Ali Khan Rashid, Fasiha Ashraf, Hafiz Abdul Rehman

International Journal of Innovations in Science and Technology · 06.05.2026 · 825

DOI: 10.33411/ijist/1886 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovations in Science and Technology, online erschienen am 06.05.2026. Verfasst von Saim Anwar und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Financial markets today depend largely on opaque algorithms. Although they have strong predictive capability, they are often non-transparent, which creates difficulties in meeting compliance requirements and establishing trust. In this work, a new hybrid Neuro-Symbolic Trading System is introduced, which is designed for the EUR/USD currency pair in forex. The method combines the interpretability of Fuzzy Logic with the predictive capability of Automated Machine Learning (AutoML). Heuristic rules based on the experience of traders, like trend-line bounce-offs and geometric analysis of resistance levels, are converted to linguistic terms in the fuzzy logic environment. These rules are optimized using the FLAML (Fast and Lightweight AutoML) library. The effectiveness of the model was evaluated using a dataset comprising 372,379 instances of high-frequency M1 readings for the year 2024. In comparison to the 58.2% prediction accuracy of the conventional technical indicator-based system, the hybrid model has a 79.4% prediction accuracy, a precision of 78.1%, a recall of 77.6%, a Sharpe Ratio of 2.34, an ROI of 142.7%, and a maximum drawdown of 7.2%. Moreover, the proposed methodology makes use of an XAI layer called Time-Aware Explainable AI, which uses the ShaTS technique. This ensures that model decisions are supported by temporally-aware feature attribution in accordance with governance requirements [1]. Through the adoption of fuzzy logic, this research highlights the possibility of improving predictive accuracy while addressing the problem of the "Black Box".

Zitieren

APA

Anwar, S., Rashid, H. A. K., Ashraf, F., & Rehman, H. A. (2026). Explainable Hybrid Forex Trading: Integrating Fuzzy Price Action with AutoML. International Journal of Innovations in Science and Technology, 825. https://doi.org/10.33411/ijist/1886

Vancouver

Anwar S, Rashid HAK, Ashraf F, Rehman HA. Explainable Hybrid Forex Trading: Integrating Fuzzy Price Action with AutoML. International Journal of Innovations in Science and Technology. 2026:825. doi:10.33411/ijist/1886

BibTeX
@article{Anwar2026,
  author = {Anwar, Saim and Rashid, Haider Ali Khan and Ashraf, Fasiha and Rehman, Hafiz Abdul},
  title = {Explainable Hybrid Forex Trading: Integrating Fuzzy Price Action with AutoML},
  journal = {International Journal of Innovations in Science and Technology},
  year = {2026},
  pages = {825},
  doi = {10.33411/ijist/1886}
}
Kostenlos starten →