News for hackers. Stuff that matters.
Re:LSTM Neural Networks for Time Series Prediction by 1024core on Monday December 26, 2016 @02:11PM (#13259367)
> So... can you or can you not, predict the stocks with ANN's... haha, guess I won't be quitting my job any time soon.

Not sure about "predicting" the stocks with ANNs, but how do you explain the Medallion Fund averaging about 30%/y (ballpark) without a single loss year since 1990 ?

https://www.bloomberg.com/news/articles/2016-11-21/how-renai...

Re:LSTM Neural Networks for Time Series Prediction by argonaut on Monday December 26, 2016 @07:45PM (#13260587)
Except these firms don't use LSTMs at their core. They do tons of feature engineering combined with statistical models and very simple machine learning models (think linear/logistic regression). Some firms will use more complicated black box models (which would include LSTMs), but only as one additional signal to combine with all their hand engineered features and financial models.
Re:LSTM Neural Networks for Time Series Prediction by brobinson on Monday December 26, 2016 @03:42PM (#13259674)
Or Virtu having a single losing day in a six year period?

https://www.bloomberg.com/news/articles/2015-02-20/high-freq...

I wonder what the Sharpe Ratios of the trading systems these funds run are.

Re:LSTM Neural Networks for Time Series Prediction by nomnombunty on Monday December 26, 2016 @09:52PM (#13260982)
Virtu does high frequency trading so it makes sense that they don't have many down days. Also HFT strategies can have ridiculous sharpe ratios of like 100
Re:LSTM Neural Networks for Time Series Prediction by makeset on Tuesday December 27, 2016 @04:09PM (#13266196)
True, although conventional metrics like Sharpe ratio or ROI are not very meaningful for HFT models, because they can't scale with any additional capital (you can safely assume they are scaled to the max). Their returns are extremely consistent, but also ultimately limited in magnitude. Rather than magical money-making machines who have cracked the "secret code" of financial markets, HFTs are essentially a fixed-cost utility service for reducing market inefficiency through improved price discovery.
Re:LSTM Neural Networks for Time Series Prediction by brobinson on Tuesday December 27, 2016 @04:21AM (#13262164)
>HFT strategies can have ridiculous sharpe ratios of like 100

Yeah, I've heard similar and it explains their basically linear equity curves...