LSTM Neural Networks for Time Series Prediction
jakob-aungiers.com
LSTM Neural Networks for Time Series Prediction
1–10 of 23 posts
Re: LSTM Neural Networks for Time Series Prediction
#2So... can you or can you not, predict the stocks with ANN's... haha, guess I won't be quitting my job any time soon.
>A stock time series is unfortunately not a function that can be mapped.
Re: LSTM Neural Networks for Time Series Prediction
#3The LSTM shown will or will not predict the direction of a random walk. But it does OK with a sin function.
Re: LSTM Neural Networks for Time Series Prediction
#4So... can you or can you not, predict the stocks with ANN's... haha, guess I won't be quitting my job any time soon. >A stock time series is unfortunately not a function that can be mapped.
I would say that you certainly can not predict it. But given enough information (all stocks, news, etc) sufficiently complicated LSTM-like network might be able to beat you. But feasibility of building and computing it today - I have my serious doubts :)
Re: LSTM Neural Networks for Time Series Prediction
#5So... can you or can you not, predict the stocks with ANN's... haha, guess I won't be quitting my job any time soon. >A stock time series is unfortunately not a function that can be mapped.
I would say that you certainly can not predict it. But given enough information (all stocks, news, etc) sufficiently complicated LSTM-like network might be able to beat you. But feasibility of building and computing it today - I have my serious doubts :)
Yeah I don't know anything about this stuff at this point. fantasy
Anyway thanks
Re: LSTM Neural Networks for Time Series Prediction
#6The key with autocorrelated models is to benchmark them against a naive alternative. I really appreciate Jakob's point that the LSTM might simply be modeling one step ahead using the current data point and Gaussian noise. Such a candid assessment is important in applied work.
I suspect that, similar to other time series applications, you'll find some interesting signals from exogenous effects. I wonder how LSTMs can incorporate this exogenous information for time series analysis.
Re: LSTM Neural Networks for Time Series Prediction
#7So... can you or can you not, predict the stocks with ANN's... haha, guess I won't be quitting my job any time soon. >A stock time series is unfortunately not a function that can be mapped.
I would say that you certainly can not predict it. But given enough information (all stocks, news, etc) sufficiently complicated LSTM-like network might be able to beat you. But feasibility of building and computing it today - I have my serious doubts :)
To be fair, all you really need to do in most stock market use cases is to predict measurably better than the competition to be able to get something of business value, not necessarily really close to "perfect" or within so much accuracy.
Re: LSTM Neural Networks for Time Series Prediction
#8So... can you or can you not, predict the stocks with ANN's... haha, guess I won't be quitting my job any time soon. >A stock time series is unfortunately not a function that can be mapped.
> 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
#9So... can you or can you not, predict the stocks with ANN's... haha, guess I won't be quitting my job any time soon. >A stock time series is unfortunately not a function that can be mapped.
> 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...
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
#10There's a good comment on the article about using this kind of network to predict direction rather than return. I think that's where this would show the most promise: if you know the direction that a (liquid) asset or the market will go, then you can make money via a long/short strategy.