Developing a framework for forecasting financial time series using Wavelet-LSTM hybrid model

Yenokyan, Robert

dc.contributor.advisor	Barseghyan, Gayane
dc.contributor.author	Yenokyan, Robert
dc.date.accessioned	2018-07-17T11:28:59Z
dc.date.available	2018-07-17T11:28:59Z
dc.date.created	2018
dc.date.issued	2018-07-17
dc.identifier.uri	https://dspace.aua.am/xmlui/handle/123456789/1560
dc.description	This is a BA thesis work submitted to the American University of Armenia, Manoogian Simone College of Business and Economics, by Robert Yenokyan.	en_US
dc.description.abstract	In this paper, 4 models are fitted in EUR/USD, GBP/USD, and USD/JPY rates. First LSTM model is fitted to forecast the price at the next step and is compared with Wavelet-LSTM hybrid model. The results show that the hybrid model performs better than the LSTM model without wavelet decomposition. However, mean absolute percentage error (MAPE) shows that the hybrid model performs poor for trading purposes. Then a classification problem is considered. The objective of the problem is to predict the direction of the return on the next timestamp. Again LSTM is compared with Wavelet-LSTM model. The results show that Wavelet-LSTM performs better than LSTM. The considered simple trading algorithm achieves an annualized return of 20% with Wavelet-LSTM hybrid model.	en_US
dc.language.iso	en_US	en_US
dc.subject	2018	en_US
dc.subject	AUA	en_US
dc.subject	American University of Armenia (AUA)	en_US
dc.subject	Financial Time Series	en_US
dc.subject	Wavelet	en_US
dc.subject	LSTM	en_US
dc.subject	Deep Learning	en_US
dc.subject	Forex	en_US
dc.subject	Regression	en_US
dc.subject	Classification	en_US
dc.title	Developing a framework for forecasting financial time series using Wavelet-LSTM hybrid model	en_US
dc.type	Thesis	en_US