An economic forecasting based on association rules and neural network.

The world economic environment is currently undergoing drastic changes, such as economic forecasting. It is a complex and challenging task because of the following reasons: i) there is no economic model which carries conviction, ii) economic time series are intrinsically very unreliable and generall...

全面介紹

Saved in:
書目詳細資料
Main Authors: Defit, Sarjon, Md. Sap, Mohd. Noor
格式: Article
語言:English
出版: Penerbit UTM Press 2001
主題:
在線閱讀:http://eprints.utm.my/id/eprint/8761/1/MohdNoorMd2001_AnEconomicForecastingBasedOn.PDF
http://eprints.utm.my/id/eprint/8761/
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
機構: Universiti Teknologi Malaysia
語言: English
實物特徵
總結:The world economic environment is currently undergoing drastic changes, such as economic forecasting. It is a complex and challenging task because of the following reasons: i) there is no economic model which carries conviction, ii) economic time series are intrinsically very unreliable and generally have poor signal to accurate results, iii) non stationary and iv) non linearity. In this paper we propose an economic forecasting based on association rules and neural network. Our study concludes that our model can improve the prediction ability by using frequent itemsets and predicted attribute as input fields. In this paper, we explain the important of data mining and prediction, association rule mining, the proposed economic forecasting model, testing and experimental results, model performance and conclusion.