Search results

I think SMART includes dark pools, try using a directed order ?

A trend moving up shows buyers that are getting more and more anxious to buy, therefore making higher lows. A trend line, looks pretty in the chart and makes for great eye candy for our mind which happens to be wired for identifying patterns.

Messed up the link on the prev post, here it is again. https://www.imperial.ac.uk/media/imperial-college/research-centres-and-groups/cfm-imperial-institute-of-quantitative-finance/events/Lillo-Imperial-Lecture3.pdf

HFT's and quants do a lot of work out of the limit order book, since signals on the book lead those in the tape. But the dynamics of the order book (bid and ask) are far from simple. The answer to your question is "it depends" since a large size may be a large buyer, or it may be a bluff...

Python is slower at run time, but it is much faster for iterating over ideas and building new strategies. Components of the system that almost never change (data handlers, fix engine) are best build on C or even on a FPGA but python adds value in areas that are constantly changing and require...

C++ middleware and backend, where performance matters. and front end/GUI on something else...

Jurgen Schmidhuber on Deep Learning... (he's one of the leading researchers in the field)

Andrew Ng's course is awesome. I took it a few years ago. It makes you understand how gradient descent, recomender systems and neural nets work underneath the hood. It also gives a great foundation on machine learning, understanding the high variance/high bias trade off , the linear algebra...

Found an interesting article. It states that there's no such thing as machine learning, it's just learning. It takes a few premise that basically argue that the distinction between machine and organism is not as clear as one would assume. quote: An ecorithm is an algorithm, but its...

pretty interesting read. thnx.

Check out this course on neural nets by geoffrey hinton. He covers several types of nets starting with perceptrons, then sigmoid networks, ..., all the way to restricted boltzman machines and self organizing maps. It's a great and deep introduction to deep nets (pun!) from the man who invented...

Generally and possibly indicate that different pools can behave differently depending on how they are legally setup (which specific rules apply to them and which not) and how they play within the margins given by the rules...

In this Berkley Class (it is free, of course) you get to teach Pacman how to win by himself through reinforcement learning :D https://www.edx.org/course/artificial-intelligence-uc-berkeleyx-cs188-1x

checkout the blog at quanstart.com they cover trading systems design in python and C++, elaborating in many key components (like the backtester) with detailed and well explained examples.

the rebate game is all about moving faster to get your place in the queue when the price changes... so it is a natural place for machines to displace humans (as they have been doing for years) since it doesn't need a lot of intelligence, but rather a lot of speed...

Yeah MOOCs don't have the whole $$ and GPA stress... so one can enjoy the material without worries. :D

jejeje... well, that's the feeling that I got when I started viewing the materials for this class. The prof is like, "here's an AR1 function, and you know how to derive it, how to get the first and second moment and how to solve to represent Xt's dependency on previous shocks" and he was just...

a bunch of friends can't get together for a nice dinner and a friendly chat about which stocks they're going to manipulate in the next few weeks? go figure!

The first week's review of stochastic calculus will quickly diffuse any doubts about the math level that is needed for the class. :D (pun intended)