I am trying to understand the difference between using Jump diffusion model and Neural Networks or more precisely LSTM to predict time series data regardless what that data contains for example a stock price or withdrawals from ATMs.

If I look at research papers I will find examples of Jump Diffusion model and LSTM to predict stock prices. But if I try searching literature to forecast withdrawals from an ATM I couldn't find any example pertaining to Jump diffusion model. Mostly LSTM or ANN has been used to predict withdrawals from ATM.

If I am trying to predict ATM cash withdrawals can I use Jump Diffusion model to make forecast or would that be an incorrect approach?

  • $\begingroup$ This is quite broad. What is the exact problem you’re trying to solve? $\endgroup$ – Bob Jansen May 25 '19 at 14:23
  • $\begingroup$ I've made changes. $\endgroup$ – Furqan Hashim May 25 '19 at 14:35
  • $\begingroup$ I don't know much about ATM withdrawals, but they probably follow a rather different process than stock prices. In particular ATM withdrawals have important seasonaliity (day of the week and holidays matter) and I do not think they 'jump' from one level to another like stock prices sometimes do (on a takeover or bankrupcty etc.). I doubt jump diffusion would model ATM w/d well $\endgroup$ – Alex C May 25 '19 at 17:48

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.