Time: 11:00am to 12:00noon
Venue: Room 7-208, 7/F, Lau Ming Wai Academic Building
News arrive randomly and the resulting sentiment, after quantification, behaves like a stochastic process. We propose a sentiment-driven stochastic volatility model to characterize the evolution of sentiment and its interplay with price and volatility process. Specifically, we propose a mean-reverting (Ornstein-Uhlenbeck) sentiment stochastic process to push over-optimistic/pessmistic sentiment back to neutral mood. Using the high-frequency news from Nasdaq news platform, we quantify news and model sentiment in the continuous time fashion. We find the presence of sentiment defers the speed of volatility reversion, and the simulated price through the sentiment-driven stochastic volatility model better approach the actual evolution of S&P 500 index.
|
Cathy Yi-Hsuan Chen is an associate professor at the School of Business & Economics in Humboldt-Universität zu Berlin, and associate professor of the International Research Training Group 1792 – High Dimensional Non Stationary Time Series. Her research focus is on “text mining in finance” and “risk analysis and management”. She has dedicated herself recently to text mining techniques in order to distill sentiment from news media or social media. Using the statistical analytics such as Machine Learning (e.g. SVM), Lexicon Projection, Latent Semantic Analysis, Latent Dirichlet Allocation and Topic Modelling, she analyzes the news impact on financial markets. She has published in key journals and has written important software for financial econometrics. She applies modern econometric techniques, such as copulae and ultrahigh dimensional factor models to financial data on systemic risk indicators. She has professional experience in risk modeling and management in banking industry. She is currently heading a “transfer project” between Humboldt-Universität and Deutsche Bank, and focusing on credit risk modelling and stress testing. |