Using LSTM Neural Network for Time Series Predictions in Financial Markets

Autor:	Svetoslav Zhelev, Dimiter R. Avresky
Rok vydání:	2019
Předmět:	Recurrent neural network Artificial neural network Computer science Currency business.industry Technical analysis Deep learning Financial market Econometrics Artificial intelligence Time series business Foreign exchange market
Zdroj:	NCA
DOI:	10.1109/nca.2019.8935009
Popis:	The article will test if Long Short Term Memory (LSTM) neural networks are suitable for high frequency foreign exchange (forex) trading. Major world currencies often correlate and affect each other. We will try to take advantage and we will feed time series data of several currency pairs and do correlation analysis on them. When traders do technical analysis they inspect different time periods in order to get better understanding on currency trends. We will also test if feeding the neural network with different time periods will lead to better predictions.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::3c412bc4da2f619a64a0e5777152a999 https://doi.org/10.1109/nca.2019.8935009 Zobrazit plný text záznamu