141 reputation
6
bio website
location
age
visits member for 2 years, 11 months
seen Mar 27 '13 at 20:03

Jan
22
comment Typical coefficients uses in square-root model for market impact
The short answer for models like BECS (formerly StockFacts Pro) is: it depends. They fit separate models for each exchange, and even within the US they fit NYSE vs. NASDAQ and S&P 500 vs. non-S&P 500 separately. They also use a model that contains both temporary (as above) and permanent impact terms, which would affect the regression coefficients, but in my experience the temporary coefficient ranged between ~1-1.5 for North America. Asia xJP was slightly higher (~2-3) and Japan was north of 4. I no longer use this model at my current firm, so I'm not sure how much this may have changed.
May
29
awarded  Critic
May
4
comment MPT: Adding constraint on minimum asset weight
Quite right, I completely mis-read that first part. I'll re-formulate the answer using Rglpk and post an edit shortly...
May
4
comment MPT: Adding constraint on minimum asset weight
I see you edited the original problem specification, but the second bullet (which is analogous to a group definition) can be formulated as a linear constraint as well (for an example, see: quant.stackexchange.com/questions/3089/…). For true mixed-integer problems, Rglpk also offers a fair amount of functionality (and is free, unlike CPLEX).
May
4
answered MPT: Adding constraint on minimum asset weight
May
4
comment MPT: Adding constraint on minimum asset weight
This is actually a standard linear constraint that just about any basic portfolio optimizer can handle (assuming you don't have any integer constraints, like maximum number of names). Is there a particular software package that you're using?
Apr
21
awarded  Student
Apr
21
revised Is there a standard method of scaling alpha forecasts to t-cost estimates?
added 23 characters in body
Apr
21
asked Is there a standard method of scaling alpha forecasts to t-cost estimates?
Mar
21
comment How do I find the most diversified portfolio, or least correlated subset, of stocks?
@TalFishman I've looked at replicating TOBAM's results in the past, and you're absolutely correct: an unconstrained MDP portfolio on the R1K universe typically holds 50-200 names.
Mar
20
awarded  Commentator
Mar
20
comment Time series of PCA - Sign change in factor loadings
My intent was to link to the original question, where some comments address the fact that spectral decompositions can produce eigenvectors with arbitrary signs (and some of the ways of dealing with that).
Mar
20
revised Optimizing a portfolio of ETFs
deleted 7 characters in body
Mar
19
comment Time series of PCA - Sign change in factor loadings
There's a related question that might help: link
Mar
19
comment Optimizing a portfolio of ETFs
Although you're not using Matlab, the Mathworks website has a multitude of examples that cover portfolio optimization and constraint specification using the financial toolbox that you might find useful. Function parameters for quadprog differ slightly between the two platforms, but the concepts are essentially the same.
Mar
18
revised Optimizing a portfolio of ETFs
deleted 18 characters in body
Mar
18
awarded  Editor
Mar
18
revised Optimizing a portfolio of ETFs
added 158 characters in body
Mar
18
answered Optimizing a portfolio of ETFs
Mar
18
comment Optimizing a portfolio of ETFs
What software are you using for optimization?