Computational Method for Claim Portfolio Valuation

Author

Kajdanowicz, Tomasz ; Kazienko, Przemyslaw

Author_Institution

Wroclaw Univ. of Technol., Wroclaw, Poland

fYear

2009

fDate

9-13 Nov. 2009

Firstpage

144

Lastpage

149

Abstract

The paper presents method of hybrid prediction system for debt portfolio appraisal. Based on the local area competence, time spread repayment values are predicted by means of hybrid combination of various machine learning techniques. The above methods include among others clustering of references, model selection and enrichment of input variables with prediction outputs from preceding periods. Experimental studies concern the method´s configuration influence on its general performance such as number of distinct predictors and number of competence areas.

Keywords

business data processing; financial management; learning (artificial intelligence); business process; claim portfolio valuation; computational method; debt portfolio appraisal; financial prediction; hybrid prediction system; machine learning techniques; model selection; reference clustering; time spread repayment values; Appraisal; Artificial intelligence; Companies; Cost accounting; Machine learning; Packaging; Paper technology; Portfolios; Prediction methods; Predictive models; claim appraisal; competence area modeling; financial prediction; repayment prediction;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence, 2009. MICAI 2009. Eighth Mexican International Conference on

Conference_Location

Guanajuato

Print_ISBN

978-0-7695-3933-1

Type

conf

DOI

10.1109/MICAI.2009.27

Filename

5372703