Citation Number
7
Views
32
Downloands
4
Araştırmanın amacı, sigorta sektöründe kasko sigortası için sahte hasarların tespitinde hasar dosyası incelemelerine yardımcı olabilecek makine öğrenmesi modelleri geliştirmektir. Bu çalışmada özel bir sigorta şirketinin kasko sigortasına ait hasar verileri kullanılmıştır. Model oluşturulmasında k-en yakın komşuluk, karar ağaçları, lojistik regresyon, yapay sinir ağ algoritmaları denenmiştir. Elde edilen sonuçlar doğrultusunda makine öğrenimi yöntemlerinin kullanımının suistimali hasarların tespiti için hasar ekiplerine ve sigorta şirketlerine yardımcı olabileceği düşünülmektedir.
The purpose of the research is to develop machine learning models that can help investigate the damage file in the detection of false damages for casco insurance in the insurance industry. In this study, the damage data of a private insurance company’s casco insurance was used. In the creation of the model, k-most closest neighbourhood, decision trees, logistical regression, artificial nerve network algorithms have been tested. According to the results obtained, it is believed that the use of machine learning methods could help damages teams and insurance companies to detect misconduct damage.
The aim of this research is to develop machine learning models that can assist in the investigation of automobile insurance claims by detecting counterfeit damages filed in the insurance industry. In this study, automobile insurance claims data belonging to a private insurance company is used for analysis. The k-nearest neighborhood, decision trees, logistic regression, and artificial neural network algorithms have been explored in data modeling. Based on the research results, it is observed that the use of machine learning methods can help claims investigation teams and insurance companies to detect fraudulent activities.
Field : Eğitim Bilimleri; Fen Bilimleri ve Matematik
Journal Type : Uluslararası
Article Detail 
Citation Owners
Similar Articles
Download PDF
Journal Information
Listen Paper
Print This Page
Share
Mendeley
