RT Journal Article
T1 Managing extreme cryptocurrency volatility in algorithmic trading: EGARCH via genetic algorithms and neural networks.
A1 Alaminos, David
A1 Salas-Compás, María Belén
A1 Callejón-Gil, Ángela
K1 Criptomoneda - Modelos matemáticos
K1 Redes neuronales artificiales
AB The blockchain ecosystem has seen a huge growth since 2009, with the introduction ofBitcoin, driven by conceptual and algorithmic innovations, along with the emergence of numerous newcryptocurrencies. While significant attention has been devoted to established cryptocurrencies likeBitcoin and Ethereum, the continuous introduction of new tokens requires a nuanced examination. Inthis article, we contribute a comparative analysis encompassing deep learning and quantum methodswithin neural networks and genetic algorithms, incorporating the innovative integration of EGARCH(Exponential Generalized Autoregressive Conditional Heteroscedasticity) into these methodologies. Inthis study, we evaluated how well Neural Networks and Genetic Algorithms predict “buy” or “sell”decisions for different cryptocurrencies, using F1 score, Precision, and Recall as key metrics. Ourfindings underscored the Adaptive Genetic Algorithm with Fuzzy Logic as the most accurate andprecise within genetic algorithms. Furthermore, neural network methods, particularly the QuantumNeural Network, demonstrated noteworthy accuracy. Importantly, the X2Y2 cryptocurrencyconsistently attained the highest accuracy levels in both methodologies, emphasizing its predictivestrength. Beyond aiding in the selection of optimal trading methodologies, we introduced the potentialof EGARCH integration to enhance predictive capabilities, offering valuable insights for reducingrisks associated with investing in nascent cryptocurrencies amidst limited historical market data. Thisresearch provides insights for investors, regulators, and developers in the cryptocurrency market.Investors can utilize accurate predictions to optimize investment decisions, regulators may consider implementing guidelines to ensure fairness, and developers play a pivotal role in refining neuralnetwork models for enhanced analysis.
PB American Institute of Mathematical Sciences
YR 2024
FD 2024
LK https://hdl.handle.net/10630/32302
UL https://hdl.handle.net/10630/32302
LA eng
NO Alaminos, D., Salas, M. B., & Callejón-Gil, Á. M. (2024). Managing extreme cryptocurrency volatility in algorithmic trading: EGARCH via genetic algorithms and neural networks. Quantitative Finance and Economics, 8(1), 153-209.
NO Política de acceso abierto tomada de: https://www.aimspress.com/index/news/solo-detail/openaccesspolicy
NO This research was funded by the Universitat de Barcelona, under the grant UB-AE-AS017634.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 19 ene 2026