Name
Title | ||
|---|---|---|
Integration of Batch Weighted Method with Classifiers Combination to Solve Financial Distress Prediction Concept Drift |
Abstract | ||
|---|---|---|
With the economy developing, effective financial distress prediction methods of artificial intelligence have got more and more attention of the academia. Concept drift in a data flow is another hot research topic. This paper firstly introduces several kinds of existing batch weighted methods for financial distress prediction modeling, and analyzes their shortages. To find a solution to deal with them, we proposed a new batch weighted method base on classifier combination, which applies different classification algorithms respectively in batch weighting and classifier modeling, and output the financial distress prediction result by weighted voting combination of multiple classifiers. Empirical experiment is carried out with the financial data selected from Chinese listed companies, and the proposed method is proved to be effective. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/CSO.2014.103 | CSO |
Keywords | Field | DocType |
artificial intelligence,financial distress prediction,batch weighted method,pattern classification,financial data processing,financial distress prediction methods,classifier modeling,concept drift,chinese listed companies,financial distress prediction concept drift,classifier combination,financial distress prediction modeling,sun,support vector machines,predictive models,classification algorithms,accuracy,testing | Data mining,Weighting,Computer science,Support vector machine,Concept drift,Weighted voting,Artificial intelligence,Classifier (linguistics),Statistical classification,Machine learning,Financial distress,Data flow diagram | Conference |
ISSN | Citations | PageRank |
2158-799X | 1 | 0.36 |
References | Authors | |
2 | 2 | |