A Comparison of Forecasting Techniques Efficiency for Financial Stress Data using Data Mining Techniques

Abstract

The purpose of this research is to study and compare the forecasting techniques which are suitable with the financial stress data. In this research, three techniques including linear regression, Artificial Neural Networks, and Support Vector Machine, have been selected. In order to find the best of effectiveness for the financial stress data forecasting. The result shows that Support Vector Machin gives the best performance in terms of the square root of the mean squared error (2.58). The second one is the artificial neural network that gives the square root of the mean squared error = 3.34. Linear regression provides the lowest performance (the square root of the mean square error = 82.49). Key word: Linear Regression, Neural Network, Support Vector Machine