DocumentCode :
2729001
Title :
Neural nets vs. expert systems: predicting in the financial field
Author :
Bowen, J.E. ; Bowen, W.E.
Author_Institution :
CompEngServ Ltd., Ottawa, Ont., Canada
fYear :
1990
fDate :
5-9 May 1990
Firstpage :
72
Abstract :
Compares actual data against two methods (a hybrid expert system and a neural network) for predicting a required number based upon past data and known future events. The purpose of the project was to find the best technical approach to predict required values in this type of domain. The significant contributions of this project were applying and comparing AI techniques for prediction of the required loads. The two criteria for success are the accuracy and the reliability of the prediction. Two important results have been obtained: the hybrid expert system predicts better than the human expert, and the neural net has demonstrated that it has the capability at least equal to the expert
Keywords :
expert systems; filtering and prediction theory; financial data processing; neural nets; reliability; AI techniques; accuracy; financial predictions; hybrid expert system; load prediction; neural network; reliability; technical approach; Artificial intelligence; Banking; Costs; Expert systems; Finance; Financial management; Neural networks; North America; System testing; Telephony;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Artificial Intelligence Applications, 1990., Sixth Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-2032-3
Type :
conf
DOI :
10.1109/CAIA.1990.89173
Filename :
89173
Link To Document :
بازگشت