A0362
Title: Tensor dynamic conditional correlation model: A new way to pursuit "Holy Grail of investing"
Authors: Ke Zhu - University of Hong Kong (Hong Kong) [presenting]
Abstract: Style investing creates asset classes (or the so-called "styles") with low correlations, aligning well with the principle of the "Holy Grail of investing" in terms of portfolio selection. The returns of styles naturally form a tensor-valued time series, which requires new tools for studying the dynamics of the conditional correlation matrix to facilitate the aforementioned principle. Toward this goal, a new tensor dynamic conditional correlation (TDCC) model is introduced, which is based on two novel treatments: Trace-normalization and dimension-normalization. These two normalizations adapt to the tensor nature of the data, and they are necessary except when the tensor data is reduced to vector data. Moreover, an easy-to-implement estimation procedure is provided for the TDCC model, and its finite sample performance is examined by simulations. Finally, the usefulness of the TDCC model is assessed in international portfolio selection across ten global markets and in large portfolio selection for 1800 stocks from the Chinese stock market.
