New rule based classification algorithm for automobile insurance fraud detection

Other Title(s)

خوارزمية جديدة للتصنيف المبني على القواعد في اكتشاف احتيال التأمين على المركبات

Dissertant

al-Ali, Ahmad Uqlah Ali

Thesis advisor

Fayiz, Fadi

Comitee Members

al-Hamami, Ala Husayn
al-Jabir, Fadi Abd
al-Awanih, Ali

University

Philadelphia University

Faculty

Faculty of Information Technology

Department

Department of Computer Science

University Country

Jordan

Degree

Master

Degree Date

2013

English Abstract

-Automobile Insurance Fraud (AIF) is a significant and costly problem for both policyholders and insurance companies.

The fraudulent activities may affect negatively on the profits of automobile insurance companies.

Data mining especially rule based classification algorithms can contribute in helping the detection of fraudulent activities.

In these algorithms the output is represented in simple interpreted "If-Then" knowledge and stored in a knowledge base.

However, the problem of rule based classification such as (PRISM) generates large number of rules.

Since maintaining and understanding these classifier rules depend on classifiers size which is hard by the typical end user.

Moreover, some correlation rules in (PRISM) that near perfection ones can't be extracted.

These disappeared rules in competitive environment are considered very significant in the prediction phase.

On the other hand, induction rule based algorithm i.e.

Repeated Incremental Pruning to Produce Error Reduction (RIPPER) have small size classifiers with often low accuracy, these rules is not feasible regarding to the (AIF) classification problem, because some knowledge are undetected.

This thesis investigates the applicability of strength threshold based covering method on the problem of detection the accident type in order to make balance in producing the number of generated rules without impacting on the classification rate.

The new algorithm named Strength Threshold Based Coverage Prism (STBCP) that makes balance, (as a result on average size classifiers) in producing the rules.

This balance is accomplished by producing a new rule based classification algorithm (STBCP) that utilized a new learning, pruning and prediction procedures based on different strength threshold values (2%, 3%, 4%, 5%, and 6%) against "autos" data set using significant and complete features (More details in Chapter Three).

Based on those threshold values (2-6%), the experimental results found that, the (STBCP) algorithm produced the highest accurate classifier than PRISM, RIPPER and J.48 decision tree algorithms.

We chose (4% as average of threshold values) and we found that, STBCP algorithm produced the highest accuracy compared with PRISM, RIPPER and J.48 decision tree algorithms.

In general, the STBCP algorithm produces neither in large nor in small numbers of rules xiii (classifiers), but it make balance between them (as a result on average size).

These allow end user and decision makers to maintain and understand the produced rules with a clear representation without impacting on the classification rate (accuracy).

Main Subjects

Information Technology and Computer Science

Topics

• Islamic jurisprudence
• Insurance
• Vehicles
• Data processing
• Data mining

No. of Pages

73

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-544029