Multiscale Signal Processing for Financial Machine Learning

Develop signal processing techniques to study the multiscale behaviors of financial asset and derivative prices

Generate new multiscale features for financial machine learning, with applications to risk estimation and forecasting

Adaptive Complementary Ensemble EMD and Energy-Frequency Spectra of Cryptocurrency Prices [pdf;link], International Journal of Financial Engineering, 2021 (w. Theo Zhao)

Financial Time Series Analysis and Forecasting with HHT Feature Generation and Machine Learning, [pdf], Applied Stochastic Models in Business and Industry 2021(w. Theo Zhao)

Multiscale Decomposition and Spectral Analysis of Sector ETF Price Dynamics [pdf; link], Vol. 14, Issue 10, p.464, Journal of Risk and Financial Management, 2021 (w. T. Zhao)

Multiscale Volatility Analysis for Noisy High-Frequency Prices [pdf; DOI], Risks, 11(7), 117, 2023  (w. Theo Zhao) *cover story 

A Noisy Fractional Brownian Motion Model for Multiscale Correlation Analysis of High-Frequency Data, [pdf, DOI] Mathematics 12(6), 2024 (w. Theo Zhao) Special Issue Advanced Statistical Applications in Financial Econometrics)