Title :
Computational Method for Claim Portfolio Valuation
Author :
Kajdanowicz, Tomasz ; Kazienko, Przemyslaw
Author_Institution :
Wroclaw Univ. of Technol., Wroclaw, Poland
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;
Conference_Titel :
Artificial Intelligence, 2009. MICAI 2009. Eighth Mexican International Conference on
Conference_Location :
Guanajuato
Print_ISBN :
978-0-7695-3933-1
DOI :
10.1109/MICAI.2009.27
