Actually, the backtests are currently coming out with a Sharpe of 8, so I'm inclined to think there's something wrong with them. It's quite challenging to backtest market making though. I've got a naive simulation (similar to what I did for futures/trend following). I'll try to build a more elaborate simulation using this https://github.com/paritytrading/parity , and try and simulate latency.
Hello @globalarbtrader. I've been doing some modifications to pysystemtrade in order to live trade. Right now, pysystemtrade is raising an error and I think you should know. I was trying to make a combined forecast using your futures 'pre_baked' system. I created an issue in Github. https://github.com/robcarver17/pysystemtrade/issues/74
@globalarbtrader Is it possible to get pysystemtrade version 0.16.0? I could not find it on github. Thank you.
Because it is what is traded. "Trading is conducted for delivery during the current calendar month; the next two calendar months; any February, April, August, and October falling within a 23-month period..." It is where your volume is, and where it will be.
Hahaha I hope so! But I really think the backtests are flawed, or otherwise, a lot of the overall uptrend of crypto is leaking into the results. On an aside note though, for anyone holding Palladium futures, it's been a great week!
In general, whenever trading delta-one products that have/had a very skewed distribution or a strong drift, you might want to break your trades into initiated buys and sells, with separate statistics.
Hey guys, how can i find a subset of instruments to trade based on minimising instrument correlation without using brute force optimization technique? Say there are 45 instruments in database and I want to pick N. Right now I'm thinking a clustering algo based on correlation
That, my friend, is an "maximum edge weight clique problem" and it's pretty darn hard to solve. There are alignment-style algorithms that approximate the solution, though.