507 reputation
59
bio website
location Chicago, IL
age 30
visits member for 3 years, 7 months
seen Dec 20 '13 at 17:37

My name is Kiril Gantchev, I'm a software engineer and my interests include: machine learning, artificial intelligence, bitcoin, trading and making the world a better place!

I blog about technology in general (mostly things I encounter):
codesprout.blogspot.com

Sometimes I blog about ML/AI stuff:
mlai-lirik.blogspot.com

P.S. If you're wondering, my gravitar image is an endogenous retrovirus.

kgan...@gmail.com


Dec
18
comment How can I calculate the margin requirements for a Bitcoin futures contract?
Given the volatility, I would think that it might make sense to allow overnight, weekly, and monthly contracts. In some of those case a 50% margin might not be so horrible.
May
1
comment Arbitrage between markets
I guess my terminology was off... short selling is the same as shorting. I just thought that calling it "short selling" is redundant, but I guess it's the official term.
May
1
comment Arbitrage between markets
I'm familiar with how shorting works in general, but I'm not very familiar with arbitrage. You helped a lot with the arbitrage explanation, but then I was trying to figure out how to "simulate" shorting on an exchange that does not allow it in order to do arbitrage. Buying the inverse currency pair seems to behave like shorting a currency pair.
Apr
28
comment Arbitrage between markets
Ah, turns out you can do arbitrage with currency even if shorting is not allowed... for example: if I'm supposed to short USD/EUR, I can just buy the EUR/USD and that should be the same.
Apr
27
comment Arbitrage between markets
The terminology is confusing me a bit: "selling something short". As far as I understand it, taking a short position occurs when you're selling something which you don't have. Simply selling something implies that you have it. So I find the term "selling short" to be confusing: you're either selling or shorting, but I don't know how you can do both. It's much more difficult (time consuming and expensive) to transfer non-X currency between the markets I'm dealing with, but it's possible...
Apr
27
comment Arbitrage between markets
I guess the other option is to simply get a lot of funds and buy X in market A, transfer X to market B, sell X, then take the long trip around (could be a couple of days) to re-fund A. If the flow is consistent and the money is big enough, then it might be feasible. Thanks for all of your help!
Apr
27
comment Arbitrage between markets
Oh, so you're describing pairs trading, I thought your example involved transferring currency. Is it possible to do pairs trading on a market that doesn't allow shorting?
Apr
26
comment Arbitrage between markets
That's a very helpful answer! However, if you buy Y for $0.311, you're holding Y and you can't transfer it to A to sell it. Same thing with buying Z in A, you're holding Z and you can't transfer it to C to sell it. The only thing that can transfer between the exchanges is X. I think I like the idea of pairs trading better, it might be a better option to trade when the correlation weakens...
Apr
25
comment Arbitrage between markets
@QuantGuy yes, but that presumes that if that you can "easily" take your currency between adjacent markets in currency other than X. In the situation I'm exploring, it's only feasible to move currency X between the markets, which seems to defeat the purpose of arbitrage (or at least that's how I see it).
Apr
17
comment What benchmark/index to use for backtesting a portfolio of stock options?
@JonnyBoats gotcha, thanks for the useful information! +1 for the answer btw!
Apr
17
comment What benchmark/index to use for backtesting a portfolio of stock options?
Of course the "risk-free interest rate" is not really risk-free, but it's commonly referred to as such. I was just asking if that would be a good universal benchmark to test against.
Apr
17
comment What benchmark/index to use for backtesting a portfolio of stock options?
I presume that this is where the risk-free interest rate comes into play, so the standard benchmark would be to compare your performance with the risk-free interest rate and see if you can beat it. The more circumstances you can beat it in, the better your algorithm.
Feb
6
comment How to combine various equity measures into a single measure (vector magnitude)
@shabbychef, I'm trying to figure out a way to "collapse" the vector so I don't have to compare each metric separately. I have thousands of instances to compare and I want to do it as fast as possible. Comparing 5 dimensions is going to be much slower than just comparing a single value.
Feb
4
comment How can I go about applying machine learning algorithms to stock markets?
@Neil: semantics... maybe it's not the general consensus, but the attitude towards AI is that it's voodoo science and you try it if you have $800 million to blow. I don't have such an attitude, but when I talk to various people I get that vibe.
Feb
3
comment How are risk management practices applied to ML/AI-based automated trading systems
@shabbychef: If it was easy, everybody would be doing it... some people do give up. The assumption is that your trader (or algorithm in this case) is pretty good, but you need proper risk management to establish correct lot sizes, track exposure and controlling losses. The risk management you're talking about does not address those things.
Feb
2
comment How are risk management practices applied to ML/AI-based automated trading systems
@shabbychef, OK, you're thinking of a completely different architecture for an ML system...
Feb
2
comment How are risk management practices applied to ML/AI-based automated trading systems
@shabbychef, like I said: there is no backtesting! If you hire a trader you don't backtest the trader to see how they're going to do, instead you let them trade with a paper trading account and once you see that they're doing good you actually let them trade with real money. You take the same approach with ML: you train your ML with a rolling training set, once you reach sufficient performance you start paper trading and that is effectively your "backtest." The training does not stop even if you start trading with real money, that's why you need a separate measure for risk.
Feb
2
comment How are risk management practices applied to ML/AI-based automated trading systems
@shabbychef, online machine learning eliminates the use of back-testing. The point of online machine learning is that you never stop learning: your machine learner constantly generates viable candidates (i.e. strategies) as you continue to feed it the latest market data. This also nearly eliminates datamining bias as you don't have a fixed data set on which you can overfit your ML, the data set is constantly changing.
Feb
2
comment How are risk management practices applied to ML/AI-based automated trading systems
@shabbychef I think online machine learning can mitigate those risks for the most part.
Feb
1
comment What broker/feed/APIsetup allows for recording the most accurate data (cheaply)?
@allen, it should be pretty easy to check if you download the T4 desktop and open up one of the sample projects from the installation directory. I think you will also need Visual Studio 2008 or later.