Time Series Prediction Using LSTM Deep Neural Networks
altumintelligence.com
Time Series Prediction Using LSTM Deep Neural Networks
1–10 of 72 posts
Re: Time Series Prediction Using LSTM Deep Neural Networks
#2I've built quite a few of these kinds of models. The real trick is to compare it against other methods AND to properly split A LOT of data. In many cases, (depending on the input data) a random walk does roughly as well as "predicting". This is because signal data (such as stock data) often just follow a random (or seemingly random) trend.
Re: Time Series Prediction Using LSTM Deep Neural Networks
#3Why does everyone naively try to predict price? No ‘traders’ are interested in predicting it - what traders do is identify good locations to enter or exit the market.
I.e. places with defined risk where you will know if you’re wrong if it goes against you by x% while you expect a y% gain if you’re right AND y>x is worth more than the number of times you’re wrong.
The types of Algos that work well for this are edge identification ones - I know this because I am (not as well as I’d like) successfully doing it.
LSTMs haven’t performed so well for me in this task but non-NN algos have. CNNs however were promising but didn’t match what I’d come up with - still searching for the holy grail that’ll make me rich!
Re: Time Series Prediction Using LSTM Deep Neural Networks
#4Seems to me that this is almost dangerous unless the uncertainty (and therefore confidence) of the prediction can be quantified.
Re: Time Series Prediction Using LSTM Deep Neural Networks
#5So, curve fitting?
Re: Time Series Prediction Using LSTM Deep Neural Networks
#6Why does everyone naively try to predict price? No ‘traders’ are interested in predicting it - what traders do is identify good locations to enter or exit the market. I.e. places with defined risk where you will know if you’re wrong if it goes against you by x% while you expect a y% gain if you’re right AND y>x is worth more than the number of times you’re wrong. The types of Algos that work well for this are edge id…
Can you point to any good sources for this? A search for 'edge identification stocks' yielded mostly irrelevant results.
Re: Time Series Prediction Using LSTM Deep Neural Networks
#7Why does everyone naively try to predict price? No ‘traders’ are interested in predicting it - what traders do is identify good locations to enter or exit the market. I.e. places with defined risk where you will know if you’re wrong if it goes against you by x% while you expect a y% gain if you’re right AND y>x is worth more than the number of times you’re wrong. The types of Algos that work well for this are edge id…
Can you share some pointers to more reading material on algos you consider more successful?
Re: Time Series Prediction Using LSTM Deep Neural Networks
#8Why does everyone naively try to predict price? No ‘traders’ are interested in predicting it - what traders do is identify good locations to enter or exit the market. I.e. places with defined risk where you will know if you’re wrong if it goes against you by x% while you expect a y% gain if you’re right AND y>x is worth more than the number of times you’re wrong. The types of Algos that work well for this are edge id…
Better, why do people think they can predict long term dynamics of what is basically a chaotic system? I think finding some small local dynamics is fine, but applying a neural network to try say something about global long term dynamics complete garbage - ie long term weather simulation, stock markets etc.
Chaotic systems can be deterministic, just that you will never be able to accurately measure all the variables to make a long term prediction accurately.
In the weather example, people know the equations that approximate how it works. Why value does a neural network bring? Knowing the equations is better understanding.
Re: Time Series Prediction Using LSTM Deep Neural Networks
#9If anyone is looking to get into machine learning, I've found "Introduction to Data Mining" very useful:
https://news.ycombinator.com/item?id=17808349
First edition: http://www.uokufa.edu.iq/staff/ehsanali/Tan.pdf
Also see "mining of massive datasets" usually available at this link, but it seems to be down: http://infolab.stanford.edu/~ullman/mmds/book.pdf
Which leads me to another point: Many of these books cost $100+. If you don't have those kind of resources, try Library Genesis. It's been very helpful for getting started.
Re: Time Series Prediction Using LSTM Deep Neural Networks
#10Could this approach be applied to a metric monitoring framework to give earlier/more accurate notifications if when a threshold would be crossed?
Typically these are triggered when e.g. 90% of a threshold has been crossed.