Design of Experiments vs. TOPSIS to Select Hyperparameters of Neural Attention Models in Time Series Prediction

2020
Yunus Emre Midilli, Sergejs Paršutins

Attention models are used in neural machine translation to overcome the challenges of classical encoder-decoder models. In the present research, design of experiments and TOPSIS methods are used to select hyperparameters of a neural attention model for time series prediction. The configurations selected by both methods are compared with out-of-sample data in time interval between January 2020 and April 2020 when global economies were significantly impacted due to Covid-19 pandemic. Results demonstrated that both selection methods outperformed each other in terms of different output features. On the other hand, our results with more than 95 % coefficient of determination and less than 0.23 % MAPE verified that neural attention models had strong capabilities in exchange rate prediction even in extraordinary situations in global economies.

Atslēgas vārdi
Design of experiments, hyperparameter, neural attention, time series, TOPSIS
DOI
10.7250/itms-2020-0004
Hipersaite
https://itms-journals.rtu.lv/article/view/itms-2020-0004

Midilli, Y., Paršutins, S. Design of Experiments vs. TOPSIS to Select Hyperparameters of Neural Attention Models in Time Series Prediction. Information Technology and Management Science, 2020, Vol. 23, 27.-34. lpp. e-ISSN 2255-9094. Pieejams: doi:10.7250/itms-2020-0004

Publikācijas valoda
English (en)