First, we document the co-existence of the time series momentum and of the term structure factors in the global commodity futures market. We demonstrate that the strategies based on the joint time series momentum and term structure trading signal outperform time series momentum only strategies and term structure only strategies. Second, we propose a Multivariate Volatility Regulated Kelly strategy, which imposes extra variance penalization compared to the Kelly criterion. We furthermore demonstrate the superiority of our method in relatively low correlated portfolios, relative to the fractional Kelly and full Kelly strategies. The simulation results and Chinese commodity future empirical results strongly support our method. Third, we combine the shrinkage theory and CUSUM change point detection in order to improve the covariance estimators. The change point embedded covariance estimator can pe1jorm better than any shrinking covariance estimators in the portfolio management. We empirically test different shrinkage estimators based portfolios in global futures markets.
| Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:753024 |
| Date | January 2018 |
| Creators | Zhou, Weifeng |
| Publisher | University of Birmingham |
| Source Sets | Ethos UK |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
| Source | http://etheses.bham.ac.uk//id/eprint/8263/ |
Page generated in 0.002 seconds