EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Algorithmic Complexity vs. Market Efficiency: Evaluating Wavelet–Transformer Architectures for Cryptocurrency Price Forecasting

Aldan Jay, Rafael Berlanga

Algorithms · 27.01.2026 · 19 (2) · 101

DOI: 10.3390/a19020101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 27.01.2026. Verfasst von Aldan Jay und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: INFORGES IT SERVICES.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We investigate whether sophisticated deep learning architectures justify their computational cost for short-term cryptocurrency price forecasting. Our study evaluates a 2.1M-parameter (M represents millions (e.g., 2.1M = 2,100,000 parameters), with all RMSE values reported in USD) wavelet-enhanced transformer that decomposes the Fear and Greed Index (FGI) into multiple timescales before integrating these signals with technical indicators. Using Diebold–Mariano tests with HAC-corrected variance, we find that all models—including our wavelet–transformer, ARIMA, XGBoost, LSTM, and vanilla Transformer—fail to significantly outperform the O(1) naive persistence baseline at the 1-day horizon (DM statistic = +19.13, p

Förderung

  • INFORGES IT SERVICES

Zitieren

APA

Jay, A., & Berlanga, R. (2026). Algorithmic Complexity vs. Market Efficiency: Evaluating Wavelet–Transformer Architectures for Cryptocurrency Price Forecasting. Algorithms, 19(2), 101. https://doi.org/10.3390/a19020101

Vancouver

Jay A, Berlanga R. Algorithmic Complexity vs. Market Efficiency: Evaluating Wavelet–Transformer Architectures for Cryptocurrency Price Forecasting. Algorithms. 2026;19(2):101. doi:10.3390/a19020101

BibTeX
@article{Jay2026,
  author = {Jay, Aldan and Berlanga, Rafael},
  title = {Algorithmic Complexity vs. Market Efficiency: Evaluating Wavelet–Transformer Architectures for Cryptocurrency Price Forecasting},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {2},
  pages = {101},
  doi = {10.3390/a19020101}
}
Kostenlos starten →