Second order stochastic dominance

[rspadim]

Could be possible use deepdow yo second order dominance portfolios?

www.kybernetika.cz/content/2008/2/243/paper.pdf

https://www.wiwi.uni-konstanz.de/typo3temp/secure_downloads/85535/0/e1c9300496b7624a1c5f62720b94796f91d46780/2014-5-19_Improved_Portfolio_Choice_using_Second-order_Stochastic_Dominance_Version87.pdf

https://ampl.com/MEETINGS/TALKS/2013_07_Bergamo_Wed.pdf

[jankrepl]

Thank you for the post. I actually never heard of this SSD concept. Really interesting.

If I understood it correctly, one can characterize (sufficient + necessary condition) the SSD efficient portfolio as a solution of some convex optimization problem, right?

If that is the case, you can use cvxpylayers to define and solve the problem. For some inspiration, check out the NumericalMarkowitz implementation here

So in short, I think it should be possible to use it inside of deepdow!

[jankrepl]

Closing due to inactivity