New Susceptible Architectures improve financial volatility forecasting

Researchers have developed a new reservoir design principle called Susceptible Architectures (SUSA) for volatility forecasting in financial markets. SUSA utilizes complex-valued reservoirs and regime-conditioned experts to analyze market states like calm, onset, recovery, and stress. Implementations include open-system q-qubit versions using Qiskit, anchored by AR-Ridge and trained with QLIKE. Evaluations on U.S. equity and ETF series demonstrated competitive performance against GARCH models, showing statistically significant improvements in QLIKE for specific assets and enhancing HARQ-style predictions through stacked ensembles. AI

IMPACT Introduces novel architectures for time-series forecasting, potentially improving quantitative trading strategies.

RANK_REASON This is a research paper detailing a new methodology for financial forecasting. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv cs.LG →

• AR-Ridge
• Qiskit
• Susceptible Architectures
• U.S.

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →