Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Ferreira, N. B., Mendes, D. A. & Mendes, V. (2024). Does data frequency mean better stock market forecasting performance? The German and US case study. 1st Artificial Intelligence in Finance Conference (AIIFC) .
Exportar Referência (IEEE) 
N. R. Ferreira et al.,  "Does data frequency mean better stock market forecasting performance? The German and US case study", in 1st Artificial Intelligence in Finance Conf. (AIIFC) , Sao Marcos, Texas, 2024
Exportar BibTeX 
@misc{ferreira2024_1734880339839,
	author = "Ferreira, N. B. and Mendes, D. A. and Mendes, V.",
	title = "Does data frequency mean better stock market forecasting performance? The German and US case study",
	year = "2024",
	howpublished = "Digital",
	url = "https://home.tpq.io/aiifc/"
}
Exportar RIS 
TY  - CPAPER
TI  - Does data frequency mean better stock market forecasting performance? The German and US case study
T2  - 1st Artificial Intelligence in Finance Conference (AIIFC) 
AU  - Ferreira, N. B.
AU  - Mendes, D. A.
AU  - Mendes, V.
PY  - 2024
CY  - Sao Marcos, Texas
UR  - https://home.tpq.io/aiifc/
AB  - This paper aims to analyze if time series frequency is related to better forecast performance. We analyze two time series from G7 economies, NASDAQ and DAX, for 5 minutes, and daily frequency. The implemented algorithms are deep learning recurrent neural networks, particularly some variations of Long Short-Term Memory (LSTM) architectures (LSTM, BiLSTM). Random search hyperparameter tuning was used to obtain the model architecture that minimize the loss function. We obtained better results for the 5-minute intraday frequency for both time series, and the forecast improved by 1%.
ER  -