DocumentCode :
175848
Title :
Predicting listing status of listed companies in China using adaboost approach
Author :
Ligang Zhou
Author_Institution :
Sch. of Bus., Macau Univ. of Sci. & Technol., Taipa, China
fYear :
2014
fDate :
19-21 Aug. 2014
Firstpage :
731
Lastpage :
735
Abstract :
It is very important for the investors to correctly predict the listing status of listed companies (LSLC) in China. This paper is the first to format the problem of predicting LSLC as a multiclass classification problem, while almost all preliminary research considered it as a binary classification problem. Adaboost method is introduced to solve the problem and the experiment result shows that it outperformed neural network and linear discriminant analysis in classification accuracy.
Keywords :
learning (artificial intelligence); neural nets; pattern classification; stock markets; Adaboost method; China; LSLC; adaboost approach; binary classification problem; linear discriminant analysis; listing status of listed companies; multiclass classification problem; neural network; Accuracy; Companies; Linear discriminant analysis; Predictive models; Stock markets; Testing; Training; Multiclass classification; listing status; predicting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation (ICNC), 2014 10th International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4799-5150-5
Type :
conf
DOI :
10.1109/ICNC.2014.6975927
Filename :
6975927
Link To Document :
بازگشت