Re:Lessons learned building an ML trading system
by smabie on Wednesday November 27, 2019 @06:02PM
(#21653042)
How do you maintain a market neutral portfolio without the ability to go short? Also I would be interested in hearing about your Sharpe ratio. Thanks! Great article!
Re:Lessons learned building an ML trading system
by traK6Dcm on Wednesday November 27, 2019 @06:13PM
(#21653123)
You can't go short but you can still hedge your exposure by going on short on something very correlated - like Bitcoin futures. I do this manually depending on how much capital I'm trading.
I actually have no idea what my Sharpe ratio is, sorry. With the system constantly changing, data formats changing, exchange balance apis changing, and accurate monitoring already being a challenge in itself, it's very difficult to keep track of exact returns and historical data. I could probably calculate it if I spent several days (weeks?) trying to process all my historical trade data, but that would be a waste of time for me personally.
Re:Lessons learned building an ML trading system
by smabie on Thursday November 28, 2019 @12:11PM
(#21658807)
If you don’t know your Sharpe, how do you know you are actually making alpha? Without knowing your return and volatility, you can’t really evaluate the performance of your algo or know if changes are helping.
But there are no pure market downturns. On a daily scale the market may be down, but that does not mean that on a millisecond or second-scale you will only see downward movement. There is just an overall downtrend, but there is still almost the same upward movement to make money. For HFT systems, it really doesn't matter if the market, on a daily scale, goes up or down. There is no difference.
In fact, on many markets the system does better in downward trends. Probably because there is more liquidity on that side of the book, a bias that may come from certain market participants.