I have some orderbook data, including 5 ask prices, 5 bid prices, amount of asks and bids for every price, and midprice which is equal to (best bid + best ask)/ 2.

available data

I would like to predict absolute change of price in a few days.

Let's say my target is:

target[i] = midprice[i+4] - midprice[i]

Which features could impact the target value?

I've tried volatility, rate of change of midprice, absolute change of midprice, order amounts change and different combinations of ROC and MA. So far, nothing has worked better than just taking all the amounts separately

  • $\begingroup$ Are you looking at feature importance from an ML model? $\endgroup$ – Quantoisseur Aug 22 '20 at 17:02
  • $\begingroup$ I'm sorry, could you explain your question? $\endgroup$ – dsddfsd Aug 22 '20 at 17:53
  • $\begingroup$ How are you evaluating whether a feature is relevant for prediction? Are you using a machine learning model? $\endgroup$ – Quantoisseur Aug 22 '20 at 19:34
  • $\begingroup$ Yes, I do. Would you recommend using something else? $\endgroup$ – dsddfsd Aug 23 '20 at 8:46
  • $\begingroup$ if you are using a machine learner for feature importance, which models have you tried or have in mind, and why do you think they are relevant for this task and data? $\endgroup$ – develarist Aug 23 '20 at 18:52

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.