Models¶

Simple Mean Variance Optimization¶

The simple mean variance optmization is a technique to optimally allocate investments between assets. The gaol is globally reduce risk on investment at a specified expected return based on the covariance between asset groups. In a Simple MVO, the expect inputs are, expected return of assets and correlation matrix between assets. Given this, the optimization algorith will be able to output an optimal portfolio weight.

In previous manuals you will have already learned about creating assets groups as well as constraint group. These groups can now be used to create a Simple MVO with the follow code.

mvo = SimpleMVO(Asset_Group, target_return, constraints, short_sale)
optimize(mvo, parameters)

Robust Mean Variance Optimization¶

Other methods of optimization such as Robust Mean Variance Optimization can also be applied onto asset and constraint groups.

rmvo = RobustMVO(Asset_Group, target_return, constraints, uncertainty_set, uncertainty_set_size, short_sale)
optimize(rmvo, parameters)

Minimum-Variance Optimization¶

In minimum-variance optmization, the goal is to minize the risk of the portfolio.

mvar = MinVarO(Asset_Group, constraints, short_sale)
optimize(mvar, parameters)

Conditional Value at Risk (CVaR) Optimization¶

cvar = CVaRO(Asset_Group, losses, constraints, alpha, short_sale)
optimize(cvar, parameters)

Optimize Function¶

The optimize(M, parameters; solver=Default) function will optimize the models above using a solver with the parameters.

To change solvers, refer to the solver select tutorial.