Exportar Publicação

Ramos, F.R., Lopes, D.R. & Tiago E. Pratas (2022). Deep Neural Networks: A Hybrid Approach Using Box&Jenkins Methodology. In Innovations in Mechatronics Engineering II. icieng 2022. Lecture Notes in Mechanical Engineering. (pp. 51-62).: Springer International Publishing.

F. R. Ramos et al.,  "Deep Neural Networks: A Hybrid Approach Using Box&Jenkins Methodology", in Innovations in Mechatronics Engineering II. icieng 2022. Lecture Notes in Mechanical Engineering, Springer International Publishing, 2022, pp. 51-62

@incollection{ramos2022_1730118441502,
	author = "Ramos, F.R. and Lopes, D.R. and Tiago E. Pratas",
	title = "Deep Neural Networks: A Hybrid Approach Using Box&Jenkins Methodology",
	chapter = "",
	booktitle = "Innovations in Mechatronics Engineering II. icieng 2022. Lecture Notes in Mechanical Engineering",
	year = "2022",
	volume = "",
	series = "",
	edition = "",
	pages = "51-51",
	publisher = "Springer International Publishing",
	address = "",
	url = "https://doi.org/10.1007/978-3-031-09385-2_5"
}

TY  - CHAP
TI  - Deep Neural Networks: A Hybrid Approach Using Box&Jenkins Methodology
T2  - Innovations in Mechatronics Engineering II. icieng 2022. Lecture Notes in Mechanical Engineering
AU  - Ramos, F.R.
AU  - Lopes, D.R.
AU  - Tiago E. Pratas
PY  - 2022
SP  - 51-62
SN  - 2195-4356
DO  - 10.1007/978-3-031-09385-2_5
UR  - https://doi.org/10.1007/978-3-031-09385-2_5
AB  - The articulation of statistics, mathematical and computational techniques for modelling and forecasting of time series can help in the decision-making process. When dealing with the intrinsic challenges for financial time series, Machine Learning methodologies, in particular Deep Learning, was pointed out as being a promising option. Previous works, highlight the potential of Deep Neural Network architectures, but also their limitations with regards to computational complexity. Some of these limitations are analysed in this work, where a hybrid approach is proposed in order to benefit from the knowledge and solidity of Box&Jenkins methodologies and the viability of applying robust cross-validation of the neural network – Group k-Fold. Through the construction of complete and automated computational routines, the proposed model is tested with the modelling of two financial time series with disturbances on their historical data: Portuguese Stock Index 20 (PSI 20) and Standard & Poor’s 500 Exchange-Traded Fund (SPY). The approach is compared to neural network models with Multilayer Perceptron and Long Short-Term Memory architectures. Besides reducing the implicit computational time by 20%, by considering Mean Absolute Percentage Errors, the proposed model shows forecasting quality.
ER  -