DocumentCode :
661199
Title :
Data mining in insurance claims (DMICS) two-way mining for extreme values
Author :
Aftab, Shoohira ; Abbas, W. ; Bilal, Muhammad Musa ; Hussain, Tauqeer ; Shoaib, Mohammed ; Mehmood, Syed Hamza
Author_Institution :
Protege Global, Islamabad, Pakistan
fYear :
2013
fDate :
10-12 Sept. 2013
Firstpage :
1
Lastpage :
6
Abstract :
In insurance claims extreme values are inevitable and cannot be discarded for predictive model building. Moreover, settling insurance claims involves many objections, human sentiments and unseen factors which are hard to be estimated. This simple fact presents the greatest challenge to analysts working on such problems. This paper presents an optimal approach to minimize the effects of this problem on predictive analysis. The data in question includes insurance settlement cases. The proposed approach firstly deals with extreme values by classifying them separately and then applies machine learning models for predicting settlement amount for each claim. This two way mining increases the overall accuracy in predicting settlement amount for insurance claims.
Keywords :
data mining; insurance data processing; learning (artificial intelligence); DMICS; data mining; extreme values; human sentiments; insurance claims; machine learning models; predictive analysis; predictive model building; settlement amount prediction; two-way mining; unseen factors; Accuracy; Data models; Floors; Insurance; Predictive models; Regression tree analysis; Support vector machines; classification; extreme values; insurance claims; insurance settlements; machine learning; predictive model; two way mining;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Information Management (ICDIM), 2013 Eighth International Conference on
Conference_Location :
Islamabad
Print_ISBN :
978-1-4799-0613-0
Type :
conf
DOI :
10.1109/ICDIM.2013.6694026
Filename :
6694026
Link To Document :
بازگشت