Please use this identifier to cite or link to this item: https://publication.npru.ac.th/jspui/handle/123456789/808
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKaewwichit, Pichet-
dc.contributor.authorKawila, Udomsak-
dc.contributor.authorLukkananuruk, Nitima-
dc.contributor.authorHengpraphorm, Kairung-
dc.contributor.authorHengpraphorm, Supojn-
dc.date.accessioned2020-10-12T07:18:38Z-
dc.date.available2020-10-12T07:18:38Z-
dc.date.issued2020-07-10-
dc.identifier.urihttps://publication.npru.ac.th/jspui/handle/123456789/808-
dc.description.abstractThe 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 Machineen_US
dc.subjectLinear Regressionen_US
dc.subjectNeural Networken_US
dc.subjectSupport Vector Machineen_US
dc.titleA Comparison of Forecasting Techniques Efficiency for Financial Stress Data using Data Mining Techniquesen_US
Appears in Collections:Proceedings of the 12th NPRU National Academic Conference

Files in This Item:
File Description SizeFormat 
The 12th NPRU_18.pdf195.35 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.