Application of ensemble learning for views generation in Meucci portfolio optimization framework (A.Didenko, S.Demicheva)

Modern portfolio theory assumes that decisions are made by individual agents. In reality most investors are involved in group decision-making. The paper renders group decision-making process by means of random forest algorithm, which could significantly improve prediction of weak learners by combining them into one model with superior performance. We combine technical, fundamental and sentiment analysis in order to generate views on different asset classes. Then the portfolio model is built using copula opinion-pooling under views generated by random forest. The model is backtested and results are compared with the ones obtained using traditional asset allocation techniques.

(Published in «Review of Business and Economics Studies», ISSN 2308-944X, Issue I(I) – September 2013; full text available from SSRN)

Continue reading