CODEWITHSUNDEEP
roptimizationportfoliononlinear-optimization
ThatQuantDude
ThatQuantDude

Reputation: 833

right R package for portfolio optimization using nonlinear constraints

I am currently looking at rewriting a commercial "back-box" portfolio optimiser, data in -> results out. I want to move away and use my own R version of it, so far a have to implementations working for my equality constraints, "solve.QP" and "constrOptim".

My problem now is the more I move towards nonlinear constraints (especially turnover limitations and transaction costs) the less information I find, would be great if someone could recommend a package, best case already a finance package or a more general mathematical one. The few packages I read along the lines so far were, "nloptr","fportfolio" and sometimes "rmetrics".

Any examples would also be highly appreciated.

thanks

Upvotes: 0

Views: 542

Answers (1)

Erwin Kalvelagen
Erwin Kalvelagen

Reputation: 16724

Turnover constraints involve an absolute value. This can be linearized. So you can use your existing solver.

Linear transaction cost: same story. If your transaction cost have a fixed cost structure then things become more complicated. That may require an MIQP solver.

Upvotes: 2

Related Questions