Portfolio Optimization Simplified
A revolutionary way to model and solve portfolio optimization problems using R
The basic idea of conceptualizing a radically new way to model portfolio optimization problems was to build a portfolio optimization modeling language on top of a generalized algebraic modeling language. Using this concept, a simple minimum variance portfolio can be modeled as follows:
m <- model() m$variable(portfolio, lb = 0) m$minimize(markowitz(portfolio)) m$subject_to(budget_norm(portfolio))
Of course, more complex examples with creative risk measures can be added easily, e.g. consider the idea to minimize the Omega risk measure and constrain the portfolio to some CVaR as well as a Markowitz maximum constraint!
m <- model() m$variable(portfolio, lb = 0) m$maximize(omega(portfolio)) m$subject_to(cardinality(portfolio) <= 7) m$subject_to(cvar(portfolio, 0.95) <= 0.02) m$subject_to(markowitz(porfolio) <= 0.03)
And on top of that you are always able to use all standard functionalities of a generalized algebraic modeling language.
The development team consists of Laura Vana (portfolio optimization modelling), Florian Schwendinger (general optimization modeling, linking to solvers) and Ronald Hochreiter (concept and ideas).
We are organizing workshops on topics of stochastic portfolio optimization and the new portfolio optimization modeling language especially in London, Paris, Frankfurt and Vienna. If you are interested in joining one of the workshops or if you want to organize an in-house workshop for your company, please contact us.