Research Interests |
My research interests lie in venture capital/private equity/portfolio data, temporal network data and environmental data. All of them are highly correlated with time-space varying statistical methodology. My current research focuses on air quality problems. More specifically, I am working on addressing the issues of airborne fine particles PM2.5 on human health. PM2.5 raised lots of concerns, both health- and economics-related, especially in California USA and east coast of China.
|
Temporal Network |
Temporal network is the kind of network that evolves dynamically. The following is a demonstration of Enron Email Network that we looked at.
We are trying to unwinding the dependence structure of this complex system. Also, we hope to detect any anomaly promptly.
The following figure shows our clustering results via time series analysis. The following figures show some of our preliminary results on community detection of Enron Email Network at a particular week.
The following figure shows one of our methods on anomaly detection of Enron Email Network.
|
Portfolio Replication |
In investment management, people are quite interested in the problem of portfolio replication, which allows investors to manage less investment vehicles while achieving roughly the same returns as those with vast and various assets. We develop a new machine learning algorithm L1 Regularized Rolling Regression and also make inference on trading strategies based on the daily return and cumulative return space. We also incorporate hierarchical modeling and hidden Markov model to refine our results. Synthetic portfolio are constructed to simulate the performance of this parametric learning method. Real data analysis are shown to prove its capability of handling complex and low frequency data. This new method could also be generalized to unwind other problems of similar kind.
More details can be found in my master's thesis.
|