Friday, 11:00 - 11:25 h, Room: H 3027


Yuichi Takano
Control policy optimization for dynamic asset allocation by using kernel principal component analysis

Coauthor: Jun-Ya Gotoh


We utilize a nonlinear control policy, which is a function of past asset returns or economic indicators, to construct a portfolio. Although the problem of selecting the best control policy from among nonlinear functions is intractable, our previous study has built a computational framework for solving this problem. Specifically, we have shown that this problem can be formulated as a convex quadratic optimization problem by using a kernel method, which is an engine for dealing with the strong nonlinearity of statistical models in machine learning. Our nonlinear control policy resulted in better investment performance than the basic model and linear control policies could give. However, it was difficult to handle a large-scale portfolio optimization problem. Thus in this presentation, we provide an efficient solution for optimization of a nonlinear control policy by using kernel principal component analysis. Computational experiments show that our solution is effective not only in reducing the CPU time but also in improving the investment performance.


Talk 2 of the contributed session Fri.1.H 3027
"Optimal control" [...]
Cluster 7
"Finance & economics" [...]


  Florida Loans Online can help you in trying times, but be sure to know the laws necessary for your loan application. On the global pharmaceutical market this medicine was issued in 2003 by two companies - Eli Lilly and ICOS. Initially, permission to sell Cialis Sale was obtained in Europe, Australia, New Zealand.