Is it possible to use artificial intelligence for example method like reinforcment learning, LSTM, ... in predicting the price of stocks or currencies like Bitcoin, etc.? And has the work been implemented and had a positive result so far?! If the answer is yes, what is the best method?
2 Answers
I searched “machine learning finance” on Google Scholar and hid a bunch of hits.
A few jump out as being explicitly about predicting prices.
Culkin, Robert, and Sanjiv R. Das. "Machine learning in finance: the case of deep learning for option pricing." Journal of Investment Management 15.4 (2017): 92-100.
De Spiegeleer, Jan, et al. "Machine learning for quantitative finance: Fast derivative pricing, hedging and fitting." Quantitative Finance 18.10 (2018): 1635-1643.
McNally, Sean, Jason Roche, and Simon Caton. "Predicting the price of bitcoin using machine learning." 2018 26th euromicro international conference on parallel, distributed and network-based processing (PDP). IEEE, 2018.
Chen, Zheshi, Chunhong Li, and Wenjun Sun. "Bitcoin price prediction using machine learning: An approach to sample dimension engineering." Journal of Computational and Applied Mathematics 365 (2020): 112395.
Further, it’s easy to find postings about machine learning jobs at financial firms.
Consequently, I say that finance is at least interested in applying modern machine learning methods in the pursuit of accurate predictions of asset prices.
Finally, no post on financial machine learning resources would be complete without mentioning Advances in Financial Machine Learning, written by a guy from the hedge fund AQR Capital Management.
-
1$\begingroup$ Thank you for your answer and you mentioned such interesting sources $\endgroup$– aliAug 20, 2022 at 15:42
-
$\begingroup$ @all welcome to the site; please see What should I do when someone answers my question? $\endgroup$ Aug 22, 2022 at 22:05
No! I don't think so, price action and or the fluctuating value of any stock, option, commodity or currency is totally random. However, there or indicators and software out there that do make fairly good assumptions or predictions but none are not perfect I don't believe.
-
1$\begingroup$ Your answer could be improved with additional supporting information. Please edit to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers in the help center. $\endgroup$– Community BotAug 20, 2022 at 17:51
-
$\begingroup$ thank you, but how can others confirm my comment is correct or incorrect in these early stages of development? I'll simply leave the comment as is, there is no reason to change it based on facts that's not there yet and speculations are all anyone has based on past experience. thank you my friend $\endgroup$ Aug 21, 2022 at 17:04