Portfolio Construction: Using Bootstrapping and Portfolio Weight Resampling for Construction of Diversified Portfolios

In this paper we introduce a framework for constructing portfolios, addressing two of the major problems of classical mean-variance optimization in practice: Low diversification and sensitivity to information ambiguity. In order to address these issues, we incorporate a prior regarding investors preferences as well as using a bootstrapping method to incorporate the effects of input parameter variation. In the scope of the paper, we investigate these methods by the use of Monte Carlo sampling. Firstly, in order to overcome the problem on non-intuitive and undiversified portfolios, we introduce a method to construct portfolios that show a higher grade of diversification. We do this by introduction of a diversification prior on the portfolio weights, preferring portfolios that show more desired properties. In a second step, we apply bootstrapping to assess the input parameter ambiguity. By this method, more robust portfolios can be achieved. Finally we incorporate these methods into a portfolio construction procedure.