Re:Show HN: Zipline - algorithmic trading in open source Python
by jik on Friday February 01, 2013 @03:39PM
(#5153336)
You'll have to roll your own backtester though when you build your own historical DB.
Or you could just PR a new data source class for Zipline that pulls data from IB. Ah, the wonders of open source!
But to save you the time, applying regular ML to historical tick-data will only make you into a smarter market-maker. In usual trending or sideways equities, you'll make small amounts of money followed by a catastrophic loss due to catalyst events, earnings etc that wipes out months of money.
Perhaps the most important part of algo-design is not the ML, but tweaking draw-down and risk management.