020-05

第20回研究会

A possible approach to combining popular Japan equity market strategies with an emphasis on machine learning solutions †

著者 †

西山昇(Dragons' Desk, 千葉商科大学)

概要 †

We analyze the impact of advanced machine learning methods on the performance and risk characteristics of popular Japan equity strategies over the last 10 years. We then propose a possible approach to combining the findings into a single strategy and we analyze the results.

キーワード †

Historical back-testing,Machine learning,EM algorithm,GARCH,Optimization

論文 †

SIG-FIN-020-05.pdf