Ms. Yingyi Gu joined the Bloomberg Quantitative Research group in 2018. Prior to that, she earned her Master in Finance from Princeton University. At Bloomberg, Ms. Gu’s work focuses on applying innovative quantitative models across all asset classes & using machine learning methods to help reveal embedded signals in various data.
Multilinear Principal Component Analysis on Implied Volatility Surface
We model the volatility surface dynamics with Multilinear Principal Component Analysis (MPCA), a novel and natural adaptation of PCA on tensor objects. We illustrate this approach’s robustness to small sample size and how it improves the interpretability of the resulting eigen-surfaces compared to PCA.