-
C++ Programming for Financial Engineering
Highly recommended by thousands of MFE students. Covers essential C++ topics with applications to financial engineering. Learn more Join!Python for Finance with Intro to Data Science
Gain practical understanding of Python to read, understand, and write professional Python code for your first day on the job. Learn more Join!An Intuition-Based Options Primer for FE
Ideal for entry level positions interviews and graduate studies, specializing in options trading arbitrage and options valuation models. Learn more Join!
Artificial Intelligence for Algo Trading
- Thread starter D Serg
- Start date
- Joined
- 6/23/09
- Messages
- 244
- Points
- 28
'Artificial Intelligence' Gains Fans Among Investors - WSJ.com
This was in another post. My take is that it will take a long time before anyone would trust AI with a lot of money and/or volume. You learn the algo on a narrow time series, or the wrong interval and you could get disastrous results. I just don't see there being a pure AI system, it may use some elements, but no one is going to purely let it run wild.
This was in another post. My take is that it will take a long time before anyone would trust AI with a lot of money and/or volume. You learn the algo on a narrow time series, or the wrong interval and you could get disastrous results. I just don't see there being a pure AI system, it may use some elements, but no one is going to purely let it run wild.
- Joined
- 5/2/06
- Messages
- 11,764
- Points
- 273
A video on WSJ about how AI is applied in trading
- Joined
- 3/29/10
- Messages
- 117
- Points
- 38
Most HFT strategies use machine learning and/or information theory, if this is what you consider AI.
By the way, you will never see successful implementations of any strategy. That's why the (proprietary) strategies are still, you know, successful...
By the way, you will never see successful implementations of any strategy. That's why the (proprietary) strategies are still, you know, successful...
- Joined
- 2/27/11
- Messages
- 1
- Points
- 11
I am not a AI person. Then I am curious about the real-time performance. If I remember correctly, some of the classical AI algorithms are actually slow, especially when requiring a large amount iterations. Doesn't this affect the time-critical strategies, say, super high frequency trading.
D C
Grad Student
- Joined
- 3/29/10
- Messages
- 187
- Points
- 28
very interesting article from Adam Afshar, President and CEO of Hyde Park Global Investments on their implementation of AI
http://www.highfrequencytraders.com/blog/543/nonlinearity-artificial-intelligence-genetic-algorithms
http://www.highfrequencytraders.com/blog/543/nonlinearity-artificial-intelligence-genetic-algorithms
DominiConnor
Quant Headhunter
- Joined
- 9/6/06
- Messages
- 1,051
- Points
- 93
AI techniques are widespread in banks since things like optimisation and search have a lot of background in machine intelligence research.
To my certain knowledge all the main firms use AI in their prop trading, as do a lot of the smaller ones.
joel_b talks of 'trust'and there are several ways of looking at this.
Today each of the firms in the original will put billions through code directly descended from algorithms to be found in AI textbooks.
That's not quite the same as "trusting" them. Banks don't do 'trust', at least not if they want to stay being a bank long.
Independent algorithms (hereafter called KSs) are treated much like trader, with limits and oversight. If a KS seems to be losing money with no prospect, it will be curtailed and just like a trader bad losses can be fatal, but at least a trader is rarely actually deleted.
Like an organic trader a KS will often be executing flow trades, and market impact models often don't work all that well without some AI-derived techniques.
Some techniques are as skinnymonkey says really slow. I recall looking at one technique at university and saying something like "you'd need a processor running at a gighertz and literally tens of megabytes of RAM to make that work"....
Actually that's why so much of advanced programming look like AI, trying to make things that have exponential time complexity go faster and it is no coincidence that the AI community got into parallel processing so early. Functional language like Lisp or F# are inherently easier to spread over multiple CPUs.
Also there are code generation techniques like genetic programming. To an extent it doesn't matter too much how long they take because you are executing the code they build for you not the host itself.
Similar things apply to FPGAs where you can code a neural net that is pre-calibrated and runs really quite quickly, and if you are Real Programmer you'd already be looking at overcoming the issues of GPUs to do NNs on them.
To my certain knowledge all the main firms use AI in their prop trading, as do a lot of the smaller ones.
joel_b talks of 'trust'and there are several ways of looking at this.
Today each of the firms in the original will put billions through code directly descended from algorithms to be found in AI textbooks.
That's not quite the same as "trusting" them. Banks don't do 'trust', at least not if they want to stay being a bank long.
Independent algorithms (hereafter called KSs) are treated much like trader, with limits and oversight. If a KS seems to be losing money with no prospect, it will be curtailed and just like a trader bad losses can be fatal, but at least a trader is rarely actually deleted.
Like an organic trader a KS will often be executing flow trades, and market impact models often don't work all that well without some AI-derived techniques.
Some techniques are as skinnymonkey says really slow. I recall looking at one technique at university and saying something like "you'd need a processor running at a gighertz and literally tens of megabytes of RAM to make that work"....
Actually that's why so much of advanced programming look like AI, trying to make things that have exponential time complexity go faster and it is no coincidence that the AI community got into parallel processing so early. Functional language like Lisp or F# are inherently easier to spread over multiple CPUs.
Also there are code generation techniques like genetic programming. To an extent it doesn't matter too much how long they take because you are executing the code they build for you not the host itself.
Similar things apply to FPGAs where you can code a neural net that is pre-calibrated and runs really quite quickly, and if you are Real Programmer you'd already be looking at overcoming the issues of GPUs to do NNs on them.
Similar threads
