Tag Info

Hot answers tagged

17

The lead paper in the January 2011 Journal of Finance (Hendershott, Jones, and Menkveld) addresses algorithmic trading (AT). In short, they find that AT improves liquidity as measured by bid-offer spreads. Taking the econometrics as correct (it is in the Journal of Finance) the next question is if bid-offer spreads are a sufficient statistic for measuring ...


15

ML/AI systems are susceptible to a number of risks not traditionally discussed in risk management: What I call 'backtest arbitrage'. In the process of automated model generation and testing, your machine learner may discover, exploit, and concentrate on irregularities in your backtesting system which do not exist in the real world. If, for example, your ...


15

I'll take a stab at it, but this is a really broad question. A direct answer: Bayesian models often use "probability that the counter-party is informed." Indirect answers: I think your assumption is that the algorithm operates on each stock individually, and has no knowledge of what it's doing in any other stock. But, it is likely that the algorithm is ...


13

Interactive Brokers does have a .NET API, albeit a free (as in speach) one written by Karl Schulze, not IB themselves. http://www.dinosaurtech.com/utilities/ It's written in C# (and IMHO well written). I've examined both it and the Java API and find the .NET version more to my liking. That's probably just because I'm more familiar with .NET than I am ...


13

Stanford University has a free online course in machine learning with video lectures, problem sets, and even a promise of online help with coursework from Stanford faculty. This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric ...


12

This is a very interesting question. I believe it is getting a lot of up-votes from people who have wondered the same thing and don't know where to begin, whereas you have at least laid out a reasonable-sounding plan. I commend you for that. However, it is not clear to me what you're trying to learn by posting this question. In my opinion, the plan you ...


11

Regarding your order management issue, every order should have a unique identifier that the user can reference; in FIX, this is the ClOrdID. The parameters of every order the user requests should be stored in a table keyed by this identifier. If your goal is to prevent duplicate orders from going out, consider having a trade volume limit per each symbol. ...


10

This answer is my ongoing attempt to consolidate some recent commentary on this hot topic. A good place to start for anyone thinking about this question is the Economists's Buttonwood: Not So Fast, which mentions recent research by Biais and Woolley (2011) and Dichev, Huang, and Zhou (2011). Does Algorithmic Trading Improve Liquidity? This paper claims ...


10

As the others have already mentioned, this is a very broad question. Anyway, as a starting point there are some blogs that come to my mind that have some up to date high quality content on these issues from time to time: http://quantivity.wordpress.com/ http://epchan.blogspot.com/ http://www.automated-trading-system.com/ ...


10

I think R's CRAN Task Views on Machine Learning is an excellent resource for beginners moving to advanced algorithm traders. It is well-structured, broad, up-to-date, and ready-to-use! http://cran.r-project.org/web/views/MachineLearning.html I believe all advanced quantitative traders already know this. But I haven't seen anyone post it here and Flake's ...


9

I go out on a limb and say No. You can of course observe how it does, but making a prediction about how and when it decays is difficult to impossible with any degree of precision. You'd need a meta-model of the market as a whole. And, well, if you had that, wouldn't you use that knowledge to make your model better? That said, you can of course measure ...


9

Yes. First, it is much easier to proceed if you standardize the output of your forecast so they are in the same units (returns, for example, or probabilities of an event/condition occurring). After you have done this, there are 3 general approaches: Signal weighting: Then you need to define a weighting scheme for your factors. Richard Grinold has an one ...


8

Market makers place quotes on both sides (ie, the bid and the ask). Depending on the market, the MM might even be contractually obligated to provide liquidity within some threshold. NYSE's designated market makers (who replaced the specialists a few years back) are an example. Even when there is no explicit requirement, the MM will quote both sides and ...


8

The risks involved in trading is everywhere and always a multifaceted thing: it includes the volatility of the selected asset, the leverage and concentration of the porfolio, whether there is a stop loss, a hedge, etc. Also, risk management is frequently not tied to the "alpha model" directly (e.g. VaR, shortfall, and scenario testing). For instance, one ...


8

Some LinkedIn groups are particularily adequate to post these questions. Your question has already been asked in "Automated Trading Strategies" at this URL: Seeking input on QuantFactory, Deltix and 4thStory: Professional end-to-end Automated Trading Solutions. Feel free to let us know the state of your research.


8

In terms of pricing, Zen-Fire seems to be the best "retail" solution. But as you said, you need to be faster, so you can try some faster and more serious options: QuantHouse - CME's Level 1 market data will cost you around 1500 Euros per month. They have points of presence in most local financial centers in Europe (Stockholm, Frankfurt, etc.) so you can ...


8

This answer summarizes some of my comments. HFT is certainly a very hot topic these days, but it's hard to point to any one reason. A large part of it is the mystery and the profits, but also part of it is the relative novelty. Note that there is no lack of papers about medium and low frequency strategies, it's just that they are not labeled as such. Medium ...


8

We cannot give you a relative bid-ask spread that would make sense. The reason for that is that it really depends on several parameters: The type of financial asset you invest in (futures, funds, index, options, ...) The period during which you're trading (I think the liquidity in markets hasn't been the same over time). If you trade intraday, it depends ...


7

The Eurodollar market is partially pro-rata. And there is a lot of HFT on it. Getting out of the book when conditions are not right is very much HFT.


7

OpenTick used to have this... alas they are no more. But here's a link to some decent alternatives. http://blog.fosstrading.com/2009/11/opentick-alternatives.html Some have free data options, but I don't believe that any include tick level data for free. If you are in school and have access to WRDS you can get the TAQ (NASDAQ trade and quotes) which is ...


7

DSpace@MIT - High frequency trading system design and process management (non-printable) This thesis provides a detailed study composed of high frequency trading system design, system modeling and principles, and processes management for system development. Particular emphasis is given to backtesting and optimization, which are considered the most ...


7

Measuring expected shortfall (also known as conditional value-at-risk) answers the simpler question of "what is my average expected loss at the i-th quantile?" given the empirical distribution of returns. A variation is value-at-risk which measures the loss at the i-th quantile. Arguably you could leave at this this and you have your answer. You probably ...


7

Personally, I am very skeptical of the claims in "Twitter mood predicts the stock market". There are several other papers with similar claims, but not so much good quality research is available. Arguably, the sweet bits of these approaches are not public. A sounder approach is to dig at the relationship between social media activity and relate it to the ...


7

As a starting point to my answer, I would say that reading a book is not sufficient to start doing automated trading on your own as chrisaycock suggests in his comment. I would answer your questions in 3 different ways. First, building your "AI bot" which I would rather call a systematic algorithm not only requires programming skills, it also means having ...


7

Ha, interesting, so many responses with "negative" expectations. There are plenty of people that have successfully gone down this road and are producing pretty nice returns, so obviously it is possible. A trader with a smaller capital has better chances of producing good ROC with very reasonable risk parameters, simply because he's would not be constrained ...


6

There is no need to complicate things: ... d = getBdepth(); d = getOdepth(); // for the calls below pos == 0 means the best bid/offer p = getB(int pos); // bid price at pos p = getO(int pos); // offer price at pos q = getBq(int pos); // bid quantity at pos q = getOq(int pos);// offer quantity at pos Note that the above API is not the best choice if your ...


6

There is a paper of mine answering To this question: Dealing with the Inventory Risk. A solution to the market making problem by Olivier Guéant, Charles-Albert Lehalle, Joaquin Fernandez Tapia.


6

JunoTrade claims to have a streaming .NET API -- http://www.junotrade.com/index.php/junotradeapi Pinncle Trading - http://www.pcmtrading.com/technology/api.html (supports C# according to the last item). TD Ameritrade @ codeplex (unoffical)


6

The most basic strategy is beta-based quantiles. That is to say, you first control for losses on your individual stock versus overall market performance. (Your trading strategy may or may not wish to hedge away the market factor using, say, SPX futures). Then you choose a quantile, call it the 5th percentile, beyond which you consider a move to be ...


6

From this site's perspective, I think nothing would be better than a ML.SE. Finally, we got one awhile ago. UPDATE: Unfortunately, Machine Learning is merging into Cross Validated. To learn more detail, click here." I have no idea why SE admin was rush to merge ML into CrossValidated. Not a fan of it (Orz). I personally prefer a separate site. FYI, ...



Only top voted, non community-wiki answers of a minimum length are eligible