Portfolio Revisited Method 2: Multi-objective Optimization

Another technique for finding efficient portfolios is called multi-objective (or multi-criteria) optimization. You can use this technique to optimize multiple, often conflicting objectives, such as maximizing returns and minimizing risks, simultaneously. Other examples of multi-objective optimization include:

Most forms of multi-objective optimization are solved by minimizing or maximizing a weighted combination of the multiple objectives. In the portfolio example, a weighted combination of the return and risk objectives might be:

mean return – (k * standard deviation)

where k > 0 is a risk aversion constant, and the objective is to maximize the function. The relationship between return and risk for the investor is captured entirely by this one function; no additional requirements are necessary.

Geometrically, the optimal solution for a multi-objective function occurs in the saddle point between the optimal endpoints of the individual objectives. In the case of the two-objective function described previously, the optimal solution occurs somewhere on the efficient frontier between the maximum-return portfolio and the minimum-risk portfolio.

For k = 0.5, the optimal solution occurs at the point where the return minus one-half the standard deviation has the highest value.

The following sections describe the model for this problem and its OptQuest solution: