A Plus Alpha Model Proposal for Long-Short Portfolio Replication Based on Genetic Algorithms  

Oleh:

Goto, Ryosuke ; Orito, Yukiko ; Kataoka, Takayuki

Jenis: Article from Proceeding
Dalam koleksi: The 14th Asia Pacific Industrial Engineering and Management Systems Conference (APIEMS), 3-6 December 2013 Cebu, Philippines, page 1-8.
Topik: Evolutionary Algorithms; Mathematical Models; Optimization; Simulation; Financial Engineering
Fulltext: 1256.pdf (899.62KB)

Isi artikel

The portfolio optimization is to determine the proportion-weighted combination in a portfolio in order to achieve investment targets. This optimization problem is one of the combinatorial optimization problems and our focus is on the portfolio replication problem. It is difficult to find the true optimal solution in the portfolio replication problem because we do not have any techniques to solve the simultaneous equations when the number of assets is more than the number of returns data. In order to avoid this problem, we propose a plus alpha model for the long-short portfolio replication problem in this paper. Our model is an extension of the traditional replication model: a plus alpha model based on the information ratios. In the numerical experiments, we adopt a genetic algorithm to our model and the traditional replication model. And then we show that our model can optimize the portfolios with good performances in the past period than the traditional replication model does.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali