Dynamic data science applications in finance
Loading...
Date
2020-08
Authors
Zhu, Zimo
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
It has been shown that some financial data follows certain heavy tailed distributions. Thavaneswaran et al(2019) proposed a novel data-driven exponential weighted moving average (DDEWMA) volatility forecasting model to forecast the volatility directly. In this thesis, regularized DDEWMA volatility forecasting model and the data-driven neural volatility(DDNV) forecasting model are proposed to forecast volatility, value-at-risk (VaR)and expected shortfall (ES).
Moreover, the regularized DDEWMA and DDNV help improve the volatility forecasts. The DDEWMA also helps enhance the performance of portfolio optimization and algorithmic trading.
Description
Keywords
Dynamic Data Science, Volatility forecasting, Risk forecasting, Portfolio optimization, Algorithmic trading