Search results

I've been playing with the idea of moving window systems where the system is learning from the data for a period of time, but then the data "expires" and goes out of scope... The system development process... and the tools to efficiently develop new systems, and try out/discard ideas that come...

the event profiler is a tool that performs an event study over a particular pattern in the market data. http://en.wikipedia.org/wiki/Event_study it was designed by Tuckler Balch from GA Tech http://www.youtube.com/watch?v=pNLIB88XQoY yeah, I expect the signals to decay, or at least to...

You are correct, it is rather difficult to keep look-ahead bias from slipping into the system in various ways (such as the one you describe) There are several precautions in the system that are meant to prevent it from making decisions based on data that was not available at the time of the...

PostgreSQL, Python, C, C++

Hi. I'm currently working on 1 trading idea and building this framework around this idea. Although the original idea was based on 4 simple patterns using this framework i ended up splitting those 4 patterns into almost 50 patterns (by being very meticulous about where each of the 6 points...

Why are you moving away from bloomberg?

Python is one of the easiest computer languages to learn (it is often used for intro to programming courses). Any broker or provider you use is going to have pros and cons, but in everyone of these you're going to have to learn how to tell a computer what your idea is (explaining a trade idea...

BATS publishes numbers on the % of volume they represent... maybe they can be used to adjust the volume from Google?

In this case it was a Windows app. :P although I prefer to use "other" operating systems... :)

That was the idea when they bought source code from modulus... I don't know all the details but it ended up being a hassle to maintain, and the solution built on modulus was never released. And mmgment decided to build inhouse from scratch. Did it cost less than $600? Not by a long...

The market is like the weather in a nice tropical rain forest. Sometimes it is calm, but it doesn't last too long. It is usually stired up, with wind and rain. When it starts raining, its hard to know when it'll stop... it may rain for a day, it may rain for a week, but it'll stop (eventually) ...

i heard from a friend that Japan, Korea and Indonesia were offline... they said august first... but they have a tendency to say it'll come back in 2-3 weeks instead of giving a realistic estimate... so your friends may be better off trading a different market for the meantime...

I used to work for them at HO, left last year If they say 2 months, make plans for it to be offline at least 8 months...

it wouldn't be the first time...

I've seen the products from modulus before... in my previous job they paid a big pile of money for their charting solution, and ended up not using it and we went with an in house solution :(

I tried a few open source backtester recently, ended making one from scratch... That was the only way I could know every knot and bolt in the system... The open source systems were ok, but I ended up spending so much time hacking them to use the data I already have or trying to modify a small...

Check out Andrew Ng's Machine Learning Mooc, it'll give you a solid foundation. :)

why not use your current PHP code as a blue print to port into C?

sounds like you'll need some sort of ML algo, that iterates over b-c optimizing through something like gradient descent, or genetics or forests?

In that kind of time window Pyrhon will work well few instruments at a time. Python can choke pretty quickly as the number of data points grows exponentially from the additional instruments. For FIX what you need is the protocol specification from your provider, and a FIX handler (fix8 is...