Reputation
329
Next privilege 350 Rep.
Access review queues
Badges
1 9
Newest
 Explainer
Impact
~1k people reached

Apr
26
suggested rejected edit on How to express the volatility of two correlated Ito processes $Wt_1, Wt_2$ expressed in terms of $W_t$?
Apr
26
comment Finding rate of return of bond sold before maturity
The question originally had a $200 coupon (it's been edited).
Apr
25
answered Finding rate of return of bond sold before maturity
Apr
25
answered Thoughts on how quantitative hedge funds use machine learning to invest in the stock market (algorithms, examples of data, etc.)
Apr
25
comment Thoughts on how quantitative hedge funds use machine learning to invest in the stock market (algorithms, examples of data, etc.)
This is 5-10 questions rolled into one. You will get a much better and more focused response if you ask multiple questions, each of which is smaller in scope, and use the answers to previous questions to inform the next.
Apr
18
awarded  Explainer
Apr
14
comment Portfolio optimization - maximize variance with exposure to risk factors equal to zero
You can set up upper bound on variance, but still any portfolio with non-zero variance can be arbitrarily scaled so that it hits the upper bound. Your question is like asking "what values of $x$ and $y$ maximize the function $f(x,y)=x^2+y^2$". Without an upper bound on $f$ there is no solution at all. With an upper bound on $f$ there is no unique solution.
Apr
14
awarded  Commentator
Apr
14
comment Historical VaR on Commodity Physical Forward
I am still skeptical that re-pricing a million times requires grid computing (I regularly do much more intensive calculations than this on my laptop) but I will take you at your word. I updated my answer to describe a method of computing approximate VaR that doesn't require repricing for each historical point. Instead you compute some coefficients once, and then the historical P&L is a linear sum of your risk drivers.
Apr
14
revised Historical VaR on Commodity Physical Forward
updated answer
Apr
14
awarded  Editor
Apr
14
revised Historical VaR on Commodity Physical Forward
improve list formatting
Apr
14
answered Historical VaR on Commodity Physical Forward
Apr
14
suggested approved edit on Historical VaR on Commodity Physical Forward
Apr
14
answered Portfolio optimization - maximize variance with exposure to risk factors equal to zero
Apr
12
comment Geometric means, standard deviation, and sharpe ratios
@robcarver The comment at that link is incorrect. Probably the author mis-spoke. In general you should expect the arithmetic average of returns to dominate the geometric average, and the arithmetic sharpe ratio to dominate the geometric sharpe ratio.
Apr
12
answered Geometric means, standard deviation, and sharpe ratios
Apr
12
answered When and how to use RNN for stock analysis or trading
Apr
12
comment Calculating PCA hedge ratio for 3-leg spread
Always on the difference in price. If you are using data at a frequency of >= 1 day then it is better to compute relative differences, i.e $(p(t+1) - p(t)) / p(t)$.
Apr
11
awarded  Yearling