[R-SIG-Finance] Sharpe's algorithm for portfolio improvement

[Enrico Schumann]

Hi John,

what kind of "difficulty" did you encounter? If you would give more details
on what you tried, and how, then people should be better able to help you. 

I don't know the paper you mentioned, but I know a paper of W. Sharpe in
which he suggests to do repeated zero-sum changes to the portfolio, like
"increase one asset by x%, and decrease another one by x%". If that is what
you mean, this can be done with a local search. (But actually, other
functions like DEoptim should work just as well. The DEoptim package even
comes with a vignette that adresses portfolio optimisation.) 

An example for a local search procedure is given in one of the vignettes of
the NMOF package (which is available from
https://r-forge.r-project.org/R/?group_id=1128 ), even though I am not sure
how self-explanatory the vignette is.


Regards,
Enrico


  

> -----Ursprüngliche Nachricht-----
> Von: r-sig-finance-bounces at r-project.org 
> [mailto:r-sig-finance-bounces at r-project.org] Im Auftrag von 
> John P. Burkett
> Gesendet: Montag, 1. August 2011 18:49
> An: R-SIG-Finance at r-project.org
> Betreff: [R-SIG-Finance] Sharpe's algorithm for portfolio improvement
> 
> An attractive sounding algorithm for maximizing the expected 
> utility of of a portfolio was proposed by William F. Sharpe 
> in "An algorithm for portfolio improvement," Advances in 
> Mathematical Programming and Financial Planning, 1987, pp. 
> 155-170 and summarized by the same author in "Expected 
> utility asset allocation," Financial Analysts Journal, vol. 
> 63, no. 5 (Sep.-Oct., 2007), pp. 18-30.
> 
> Has this algorithm been implemented in R?
> 
> If not, is there a substitute that is likely to work well for 
> a user-specified concave utility function?  I've tried optim, 
> DEoptim, and Rgenoud but encountered difficulty in getting 
> them to converge for a long-only portfolio of around 30 assets.
> 
> Best regards,
> John
> 
> --
> John P. Burkett
> Department of Economics
> University of Rhode Island
> Kingston, RI 02881-0808
> USA
> 
> _______________________________________________
> R-SIG-Finance at r-project.org mailing list 
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R 
> questions should go.