I am trying to use LSTM network to predict stock prices. I know in real world there is a relation between the stock price and the trade volume. So I am looking a way to see if is it possible to combine stock prices and volumes and feed it as one singe input to the network instead of two separate inputs?

Most of the prices are in range of[100,1000] but the volumes are in range of [100,000 , 100,000,000]. How can I find the relation between these and find a single value to feed the network?

  • $\begingroup$ It's hard to imagine any good answer that would begin in any other way than "don't do this." You erase too much information, which in any stock market is going to be a losing approach. $\endgroup$ – whuber Mar 9 at 18:45

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.