Özet:

Considering the problems encountered due to financial risks and uncertainties, it is of great importance to determine the financial stress index. The aim of the study is to predict the level of financial stress index by using machine learning methods. For this purpose, the weekly time series of the financial stress index were examined using independent and hybrid models. While artificial neural networks are used as stand-alone machine learning models, wavelet transform is used as a preprocessing technique to create hybrid Models. In addition, lag lengths were obtained by using autocorrelation functions to increase model accuracy in financial stress index predictions. The findings of the study were evaluated in terms of various performance indicators. It has been determined that the wavelet transform artificial neural network model performs better than the pure artificial neural network model in predicting the financial stress index. It is thought that the results of the study will be beneficial for researchers and practitioners following the financial stress index.

Anahtar Kelimeler: