528 reputation
17
bio website twitter.com/experquisite
location Vancouver, Canada
age
visits member for 1 year, 9 months
seen 15 hours ago

Derivatives pricing in C++, automated trading in Scala.


Sep
16
comment How to select optimal betting strategy from backtest?
To add, why not use a clustering algorithm on the resulting profitable parameter vectors and then select the point in the center of the largest cluster?
Sep
13
comment Algo's Shadowing Limit Orders
I think you might mean "Lo and behold"
Sep
8
comment Basic question on LIBOR-OIS swap
Fed funds is the US overnight/OIS rate
Sep
6
comment Efficient Markets Paradox
Indeed. I think most of the emh stuff assumes a rational convex utility function over wealth, which is most likely not the case for most people. Eric Falkenstein has been a proponent of relative wealth utility functions being more likely, which leads to a much different landscape.
Aug
22
comment ADR vs Foriegn Stock Price Arbitraguers
fordschool.umich.edu/rsie/workingpapers/Papers526-550/r533.pdf is a study of this mechanism of evading capital controls.
Aug
22
comment ADR vs Foriegn Stock Price Arbitraguers
That concurs better with the current unofficial rate: twitter.com/SoberLook/status/501082814260211712 Perhaps people are using the ADR to get USD out of the country somehow?
Aug
21
comment What is the reasoning to derive this financial model called the Vasicek Model?
As I understand it, it was a pretty basic rationale - the short interest rate is mean-reverting, and they just supposed Gaussian diffusion. The OU process was well-known, tractable, so why not?
Aug
20
comment Approximation of different volatilities
I believe Pat Hagan did some work like this for his SABR model too, wilmott.com/pdfs/021118_smile.pdf formula A.64 may be relevant.
Aug
18
comment Testing for the presence of a positive or negative gamma effect
Maybe try a high-frequency hurst exponent test?
Aug
16
comment Calculating short/long order percentages?
You will not be able to tell short orders from sell orders, and furthermore, it doesn't look like you have any trade data at all. All you have is orders to sell and orders to buy. The problem you are going to (eventually) have is you cannot determine whether a reduction of the size on one side of the order book is caused by a fill (someone selling via taking liquidity) or by someone cancelling their resting buy order (possibly in anticipation of buying via taking liquidity).
Aug
11
comment How good is managed code for algo trading?
FWIW these days, anyone doing trading on the JVM will eventually be investigating Azul's Zing JVM, which features absolutely pause-less GC
Aug
7
comment High correlation will help detect spurious regression over cointegration?
I am not sure that the correlation really has anything to do with whether a cointegration model is spurious or not. You might get some additional insight from a principal components analysis?
Aug
3
comment Backtesting with Simulated Historical Data?
Marcos de Prado has a great paper on at least detecting this bias: trajectablog.files.wordpress.com/2013/09/…
Aug
3
comment How to build an execution trading system with CQG API?
This sort of thing is probably better automated with NinjaTrader, or perhaps Quantopian. Definitely it doesn't seem like a question for quant.SE?
Aug
2
comment Models for volatility estimation of high frequency data?
The key thing is to filter out irrelevant trades using their trade condition codes, and then handle the bid/ask bounce perhaps by marking at the mid price just smoothing it out. quant.stackexchange.com/questions/11484/… I am also hoping that amazon.com/… will cover these techniques, though I haven't gotten around to reading it yet.
Jul
23
comment What happens when bond price is less than the recovery rate
Well, if its very simple, you could set the recovery rate to 0?
Jul
23
comment What happens when bond price is less than the recovery rate
The recovery rate is not guaranteed at all, at maturity or otherwise. It's an estimate of the eventual proceeds of the sale of assets of the company, as they accrue to each particular bondholder with their rights and seniority in bankruptcy.
Jun
26
comment How to combine trading signals to achieve higher capital efficiency?
It is possible to online calculation of most of what you would need, see: thalesians.com/archive/public/academic/finance/papers/… But, as you say, perhaps that wouldn't be fast enough if you are doing HFT.
Jun
26
comment How to combine trading signals to achieve higher capital efficiency?
I've pointed out an approach that takes into account the covariance of the strategies' returns, the strength of the trading signals as well as your own risk tolerance. This is all well-trodden ground. The next level is stochastic control. But if you want to mess around talking about manually mixing and matching strategies, I guess that's your prerogative.
Jun
20
comment What broker/feed/APIsetup allows for recording the most accurate data (cheaply)?
I am evaluating activetick right now, so far so good. Next test is for cloud-hosted latency.