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

Abstract

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.

Comparative Rheological Investigation of Nanocomposites of Surface Charged Superparamagnetic Iron Oxide Nanoparticles with Polyethylene Glycol

“…The optimization of the properties of these materials can provide important information for the improvement of their mechanical properties for further applications. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is an appropriate method that has been widely applied for the optimization and prediction of various characteristics [49][50][51][52][53][54]. Some investigations on the nanocomposites of iron oxide nanoparticles with polymers have shown that these materials would be appropriate for the function improvement of electrical devices [55][56].…”