DocumentCode :
578525
Title :
Toward a new classification model for analysing financial datasets
Author :
Fan Cai ; LeKhac, N. ; Kechadi, M.
Author_Institution :
Software Sch., Comput. Sci., Fudan Univ., Shanghai, China
fYear :
2012
fDate :
22-24 Aug. 2012
Firstpage :
1
Lastpage :
6
Abstract :
Nowadays, financial data analysis is becoming increasingly urgent in the business market. As companies collect more and more data from daily operations, they expect to extract useful knowledge from existing collected data to help make suitable decisions for new customer requests, e.g. user credit category, confidence of expected return, etc. Banking and financial institutions have applied various data mining techniques to improve their decision-making processes. However, naive approaches of data mining techniques could raise performance issues in analysing very large and complex financial data. In this paper, we present a classification model for analysing efficiently these financial data. We also evaluate the performance of our model with different real-world data from transaction to stock and credit rating, etc., and we show that it is efficient, robust, and well suited for these data.
Keywords :
data analysis; data mining; finance; pattern classification; banking institutions; business market; classification model; complex financial data; data mining techniques; decision-making processes; financial data analysis; financial institutions; real-world data; very large financial data; Accuracy; Analytical models; Business; Data mining; Decision trees; Gaussian processes; Training; Classification; Gaussian Process; Neural Networks; clustering; financial data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Information Management (ICDIM), 2012 Seventh International Conference on
Conference_Location :
Macau
ISSN :
pending
Print_ISBN :
978-1-4673-2428-1
Type :
conf
DOI :
10.1109/ICDIM.2012.6360106
Filename :
6360106
Link To Document :
بازگشت