[GSoC-PortA] Mean-mETL objective?

[Brian G. Peterson]

Doug,

If the underlying solvers can do it, we should be able to pass it 
through to ROI.  There shouldn't be any inherent restriction from using ROI.

I think, based on reading your replies, that we just need to understand 
how to formulate the problem.

DEoptim only finds one minima, and it appears to be the correct one. 
'Neighbor' portfolios (the portfolios closest to the global minima by 
objective vaule) are all close in the hull space to the global minima.

Overall, I'd hope to investigate this a bit more, because if the 
formulation as a LP/QP problem is possible, it's obviously much faster 
than using random portfolios or DEoptim (or PSO, or GenSA, etc) to find 
the objective.

Regards,

Brian

On 10/05/2013 10:15 AM, Doug Martin wrote:
> *Ross Bennett wrote:
> Peter,
>
> Unfortunately, with ROI we are only able to minimize ETL with ETL as an
> objective. If you have mean and ETL as an objective using ROI, unless
> there is a target in the mean return objective, we just minimize ETL. If
> you have both mean and ETL as objectives, you could add a target to the
> mean objective and this will minimize ETL subject to the target return.
>
> */[Doug] That is unfortunate./*
>
> We can do the following with ETL as an objective using ROI:
>
>   - Minimize ETL subject to leverage, box, group, exposure, position
> limit, and target return.
>
> Multipliers are ignored with ROI since the problems are formulated into
> an LP/QP problem.
>
> */[Doug] Ditto on my comment above.  There is no problem to use solve.QP
> directly in the quadratic utility (QU) formulation of the problem (as
> well as the MinVar formulation). Should be the same for Rglpk.  So we
> are inheriting a limitation of ROI not of the solvers themselves./*
>
> *//*
>
> I'll take a look at the documentation in optimize.portfolio and make
> sure this is clear.
>
> I hope that helps clear it up.
>
> Ross
>
> On Fri, Oct 4, 2013 at 11:49 AM, Peter Carl <peter at braverock.com
> <mailto:peter at braverock.com>> wrote:
>
> Hey Ross,
>
> I can't seem to get the Mean-mETL objective to select anything other than
> the Min mETL portfolio using ROI.  It looks like there should be good
> convexity, but I think there's a substantial imbalance between the size of
> the monthly mean return and the loss indicated by the ETL.  I've tried
> modifying the multiplier on the mean, but it doesn't seem to have an
> effect.
>
> Any thoughts?
>
> pcc
> --
> Peter Carl
> http://www.braverock.com/peter
>
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> <mailto:GSoC-PortA at lists.r-forge.r-project.org>
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>
>
>
> _______________________________________________
> GSoC-PortA mailing list
> GSoC-PortA at lists.r-forge.r-project.org
> http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/gsoc-porta
>


-- 
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock