Exportar Publicação

Mendes, D. A., Ferreira, N. B. & Mendes, V. (2023). Data frequency and forecast performance for stock markets: A deep learning approach for DAX index. In Rocío Martínez-Torres, Sergio Toral (Ed.), Proceedings of the 5th International Conference on Advanced Research Methods and Analytics (CARMA2023). (pp. 39-39). Sevilha: Editorial Universitat Politècnica de València.

D. E. Mendes et al.,  "Data frequency and forecast performance for stock markets: A deep learning approach for DAX index", in Proc. of the 5th Int. Conf. on Advanced Research Methods and Analytics (CARMA2023), Rocío Martínez-Torres, Sergio Toral, Ed., Sevilha, Editorial Universitat Politècnica de València, 2023, pp. 39-39

@inproceedings{mendes2023_1732392830087,
	author = "Mendes, D. A. and Ferreira, N. B. and Mendes, V.",
	title = "Data frequency and forecast performance for stock markets: A deep learning approach for DAX index",
	booktitle = "Proceedings of the 5th International Conference on Advanced Research Methods and Analytics (CARMA2023)",
	year = "2023",
	editor = "Rocío Martínez-Torres, Sergio Toral",
	volume = "",
	number = "",
	series = "",
	doi = "10.4995/CARMA2023.2023.17009",
	pages = "39-39",
	publisher = "Editorial Universitat Politècnica de València",
	address = "Sevilha",
	organization = "CARMA23",
	url = "https://carmaconf2023.wordpress.com/proceedings/"
}

TY  - CPAPER
TI  - Data frequency and forecast performance for stock markets: A deep learning approach for DAX index
T2  - Proceedings of the 5th International Conference on Advanced Research Methods and Analytics (CARMA2023)
AU  - Mendes, D. A.
AU  - Ferreira, N. B.
AU  - Mendes, V.
PY  - 2023
SP  - 39-39
DO  - 10.4995/CARMA2023.2023.17009
CY  - Sevilha
UR  - https://carmaconf2023.wordpress.com/proceedings/
AB  - Due to non-stationary, high volatility, and complex nonlinear patterns of stock
market fluctuation, it is demanding to predict the stock price accurately.
Nowadays, hybrid and ensemble models based on machine learning and
economics replicate several patterns learned from the time series.
This paper analyses the SARIMAX models in a classical approach and using
AutoML algorithms from the Darts library. Second, a deep learning procedure
predicts the DAX index stock prices. In particular, LSTM (Long Short-Term
Memory) and BiLSTM recurrent neural networks (with and without stacking),
with optimised hyperparameters architecture by KerasTuner, in the context of
different time-frequency data (with and without mixed frequencies) are
implemented.
Nowadays great interest in multi-step-ahead stock price index forecasting by
using different time frequencies (daily, one-minute, five-minute, and tenminute
granularity), focusing on raising intraday stock market prices.
The results show that the BiLSTM model forecast outperforms the benchmark
models –the random walk and SARIMAX - and slightly improves LSTM. More
specifically, the average reduction error rate by BiLSTM is 14-17 per cent
compared to SARIMAX. According to the scientific literature, we also obtained
that high-frequency data improve the forecast accuracy by 3-4% compared
with daily data since we have some insights about volatility driving forces.
ER  -