Search results

checkout Holdbrother's graybox... as far as I know its the most "api friendly" in the prop business...

The good ole days of island and brut sub penny shavings :( If I recall correctly part of the reason why they banned subpennies, was that it was "confusing" since the prices were small enough to overlap with the maker taker fees...

thnx 4 reposting. great article. I traded TSX for a few years and was pretty familiar with its matching engine up to a couple of years ago. What they say about the way preferencing pushes people to trade with the largest brokers is very true. At one point we switched from a very small broker to...

nanex research is a good place to start, at least for the lit side of the markets...

Are they doing broker preference like they do in Toronto? Where orders that would remove liq first check if they can remove an order from the same broker and then the general queue? (Tried to read the tabb link but it seems broken)

well that sucks :( did you every hear back from LASEr?

maybe you can find some of that data on Quandl? (at least for the historical part...)

Let's get our definitions straight. So that we all speak the same language. MW dictionary defines a times series as: : a set of data collected sequentially usually at fixed intervals of time. Oxford dictionary provides this definition: A series of values of a quantity obtained at successive...

can you please explain what it is you're talking about? I don't understand the concept of a trading system without market data, regardless of the system being automated or manually traded, it needs data to function. Whether that data is SEC filings, order book, trades, auction imbalances, or...

whether you are working on a simple system based on technical indicators, or a complex machine learning bot, the system must always have the ability to generalize to out of sample data. Failure to generalize to new data indicates that the system has over-fitted (it adapted to the particularities...

All trading systems work around the time series of market data, and they seek to make probabilistic forecasts on the future data using present and past data from 1 or more sources. this is true for any trading system, whether it is manually traded or automated...

Hi Jack, I am very much aware of the fractal nature of market data, and the relative information contained in the order book and tape vs the chart. thnx. how about we stick to the threads subject and narrow down the conversation around automated trading systems?

The logic and the data should be independent, specially for machine learning systems. The logic and rules that the system applies should be able to continue working fine when the dataset changes. Otherwise it points to overfitting of the system. This is addressed during the system's design, as...

what do you mean?

check out this page it seems to have the documents you're looking for available to download: http://www.cygrouponline.com/download.html

GP has a very strong tendency to overfit the data. So they can require significant fwd testing after the paramethers have been adjusted to validate the model.

have you tried reaching out to Laser's support? have you considered that maybe the 10 year old version, is the latest spec? :(

why not start with the goal of coding some of the qualifying, categorizing and extrapolating of the data... that way you'll free some of your time as you start to code...

maybe you should checkout Ernie Chang's book. it gives a good overview of what it takes to setup an algo trading business... including details like what kind of strategies can be effectively automated. (the book includes a few strategies with excel and matlab examples)...

doesn't really takes the judgement out of the equation, just out of run time and into compile time. :D