Reputation
1,033
Top tag
Next privilege 1,250 Rep.
Create tag synonyms
Badges
6 14
Newest
 Yearling
Impact
~17k people reached

  • 0 posts edited
  • 0 helpful flags
  • 731 votes cast
Oct
24
comment Cleansing covariance matrices via Random matrix theory
I think RMT only helps you filter out noise eigenvectors. How we re-construct the correlation matrix after that is totally up to us. I personally will choose an approach that yield a diagonal of 1's. As for a diagonal != 1, it feels like that they are computing the 'cross-'correlation matrix between clean (after RMT) and noisy (before) time series (cause correlation of identical time series must equal to 1). Is it what you want? I thought we are looking for a correlation matrix composed of clean time series only.
Oct
21
awarded  Commentator
Oct
21
comment Algorithm for the choice of stocks for a equity scalper/market maker to engage in?
You can have another indicator for the competition from other market makers. The ratio of volume / quote size is a nice start. After you start trading, your real % market share and analysis of pnl will be much better indicators. Occasionally, in HFT arms race, your % market share can dramatically drop after a major competitor upgrade their system. There are also more and more HFT market 'takers' now. Analyzing your pnl to understand how many $h!t you pick up (your limit order not fast enough to run away) can tell you more story between you and your taker competitors.
Oct
18
awarded  Disciplined
Oct
9
awarded  Nice Answer
Sep
16
comment Duality between constant rebalanced portfolio (CRP) and corresponding derivative
Thank you for accepting the answer, vonjd :) And thanks for your inspiring question. I always believe it's the smart questions and curiosity that lead us to great answers and ideas! I wish I could answer you more but I really favor short and inspiring answer in public. However, I am more than happy to discuss further in private :) Please feel free to contact me (Google/Linked) if you are interested in more discussions.
Sep
16
revised Duality between constant rebalanced portfolio (CRP) and corresponding derivative
added 184 characters in body
Sep
15
revised Duality between constant rebalanced portfolio (CRP) and corresponding derivative
added 84 characters in body
Sep
15
revised Duality between constant rebalanced portfolio (CRP) and corresponding derivative
added 84 characters in body
Sep
15
awarded  Critic
Sep
15
comment Duality between constant rebalanced portfolio (CRP) and corresponding derivative
Hello Tal, please keep your bounty. I am teasing myself :) As for your question, in my opinion, once you have sound underlying dynamics, replicating is trivial. To myself, my answer is complete enough, i.e. the information I suggest here is enough to solve vonjd's questions.
Sep
15
revised Duality between constant rebalanced portfolio (CRP) and corresponding derivative
added 104 characters in body
Sep
15
comment Duality between constant rebalanced portfolio (CRP) and corresponding derivative
Oh? The bounty reward was given away while I am posting my answer? I remember there are still few hours to go before the bounty deadline? :) Too bad I just back from a vocation!
Sep
15
answered Duality between constant rebalanced portfolio (CRP) and corresponding derivative
Aug
24
comment Proof that you cannot beat a random walk
Second, there is no contradiction to the common sense that 'pure independence = zero E[PnL]'. E[] > 0 in my example and your Parrondo's paradox is indeed exploited from sort of dependency. While Parrondo exploits the dependency between two losing games, mine is exploiting the dependency on my losing trades (which is less obvious). But (warn again), this is at cost of ruin risk! Note that Kelly/Vol-pump eliminate ruin risk, but still suffer tail risk. Conclusion? Find dependency had better, create it if you must.
Aug
24
comment Proof that you cannot beat a random walk
Thank you for accepting the answer, vonjd. I also like the analogy you found in Parrondo paradox. Though not sure how to answer your questions? here is my attempt: First, all mentioned strategies propose to add(cut) risk exposure when lose(win). For example, if you long stock and you lose/gain 1 dollar when market moves, kelly or vol-pump will require you buy/sell in order to maintain constant betting ratio. This makes volatility your friend (pumping). But trend is your enemy! In this case, is random walk more like your enemy or your friend?
Aug
22
revised Proof that you cannot beat a random walk
added 53 characters in body
Aug
20
revised How do I graphically represent the evolution of a covariance matrix over time?
Move and merge some comments to the answer
Aug
20
revised Proof that you cannot beat a random walk
deleted 26 characters in body
Aug
20
revised Proof that you cannot beat a random walk
deleted 26 characters in body