RAROC, or risk-adjusted return on capital, is a measure to allocate capital on a risk-adjusted basis and to evaluate performance. In RAROC methodology risk is measured using Value at Risk(VaR), which is the expected worst loss over a given horizon at a given confidence level.
The purpose of this study is to show how to construct RAROC maximizing portfolio and to test its applicability in real world. To construct hypothetical portfolio, I picked 2 sets of 30 stocks from the ones two Korean banks actually held in Oct. 1997 and assigned the appropriate weight which could maximize RAROC of the portfolio. Then I evaluated its performance for 4 weeks by comparing the returns, VaRs, and RAROCs of two pairs of portfolios with those of actual portfolios.
The result showed the superiority of RAROC maximizing portfolio.
Of course the study has some limitations. The test period was not long enough to be sure of its applicability and I did not consider the cost of capital which can be interpreted as risk free rate in Markowitz' portfolio selection theory, and estimated VaR results can be different depending on the choice of parameters, data, assumptions, and methodology.
But RAROC maximizing methodology seems to offer a rigorous way for portfolio managers to allocate assets efficiently or at least a benchmark to assess the profitably and riskiness of their actual portfolio.