id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
hij-641	Bourday, Rachid; Aatouchi, Issam; Kerroum, Mounir Ait; Zaaouat, Ali	Cryptocurrency Forecasting Using Deep Learning Models: A Comparative Analysis	2024	13	.pdf	application/pdf	6789	462	51	The findings indicated that the Multi-Transformer and Transformer layer- based models were more accurate and provided more appropriate measures for forecasting compared to other algorithms, including those based on feed-forward layers or LSTM models. The Transformer with SVR performs better than the ANN and LSTM models, but not as well as XGboost.	cache/hij-641.pdf	txt/hij-641.txt