2022
DOI: 10.20491/isarder.2022.1549
|View full text |Cite
|
Sign up to set email alerts
|

Hile Tespitinde Makine Öğrenmesi Yöntemlerinin Kullanılmasıve Model Performanslarının Değerlendirilmesi (Using Machine Learning Methods to Detect Fraud and Evaluation of Model Performances)

Abstract: Amaç –Çalışmada,hilenin verdiği zararın azaltılmasına yönelik teknoloji temelli araçlarla çözüm üretilmeye çalışılmıştır. İşletmelerde sıklıkla karşılaşılan hileli ödemelerin tespiti için makine öğrenimi yöntemleriylebir model oluşturulması amaçlanmaktadır. Yöntem –Çalışmada, bir bankaya ait finansal ve finansal olmayanlar bilgilerle oluşturulan 594.643 adetlik yapay veri setinden yararlanılmıştır. Veri seti kullanılarak makine öğrenmesinin Karar Ağacı, Destek Vektör Makinesi, Lojistik Regresyon ve Ya… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
0
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 0 publications
0
0
0
Order By: Relevance
“…Similar results regarding the operation performed with decision tree analysis were achieved by Liou (2008) with 100%, Gür and Tarhan Mengi (2022) with 99.42%, and Gür (2023) with 98% correct detection rates. In addition to these results, when the data mining methods used together for fraud detection are compared, Kotsiantis et al (2006) and Gür and Tarhan Mengi (2022) state that the decision tree is the method that makes fast and accurate detection. This highlighted interpretation is also consistent with the result of this study.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Similar results regarding the operation performed with decision tree analysis were achieved by Liou (2008) with 100%, Gür and Tarhan Mengi (2022) with 99.42%, and Gür (2023) with 98% correct detection rates. In addition to these results, when the data mining methods used together for fraud detection are compared, Kotsiantis et al (2006) and Gür and Tarhan Mengi (2022) state that the decision tree is the method that makes fast and accurate detection. This highlighted interpretation is also consistent with the result of this study.…”
Section: Discussionmentioning
confidence: 99%
“…Rukhsar et al (2022) used the DT method to predict insurance fraud detection. Gür and Tarhan Mengi (2022) used DT, SVM, Logistic Regression, and ANNs methods to detect fraud, and it was determined that the most accurate prediction model was created by the DT method. Kılıç and Önal (2022), Kara and Özcan (2020), Terzi and Kıymetli Şen (2012) used ANNs data mining method.…”
Section: Data Mining In Fraud Detectionmentioning
confidence: 99%