Microsoft Excel sucks for quant development?
I am having a problem with Excel’s solver. The thing is that I am calculating mean-variance optimal portfolios with 126 assets. These assets do not have a lot of correlation, and in the limit, probably due to rounding circumstances + the amount of assets the Solver is having some troubles finding the optimizing points. I know, probably there are a lot of local maximas.
What would you recommend ? Should I just go MATLAB or R on this ? – My company does not have a license for these.
Actually, they are 184 assets. The variance covariance matrix is 184 x 184 which is probably a lot of meat for Mr. Bill Gates.
Oh, I’m not planning to use principle components – the whole point of this project is to explain the shift in risk vs the mix of assets and PCA eliminates this explaining power.
NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!