Decision Tree Supported Fraud Detection and an Application

Önder Gür

Makale detayları

Decision Tree Supported Fraud Detection and an Application

Yazarlar:

Önder Gür

Yayıncı:

Alanya Alaaddin Keykubat Üniversitesi

Ana Başlıklar:

Finans

Dergi:

Alanya Akademik Bakış Vol.7 Issue 1, pp.511-528

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

Türkçe

Document ID (Org No.):

2001283520

pISSN:

2651-4192

Anahtar kelimeler:

Özet:

 In the study, it is aimed to contribute to the fraud detection process with an application in which machine learning method is used to reduce the damage caused by fraudulent disbursements, which is included in the fraud tree of the Association of Certified Fraud Examiners ACFE. To achieve the desired outcomes, a Python application system is developed for this purpose. In the study, an artificial data set containing normal transactions and fraudulent transactions of a bank, was used. Using the Decision Tree technique, which was selected as the chosen method, the main model was developed using a data set with known class labels, and then the model was evaluated using unlabeled data. The model of the decision tree technique achieved 97,1 accuracy, 98,4 f1-score, 98,9 precision and 98 sensitivity. The study is open to improvement in terms of reducing the erroneous class labels produced by the decision tree technique during the estimation phase and can be improved by comparing it with other techniques.

 In the study, it is aimed to contribute to the fraud detection process with an application in which machine learning method is used to reduce the damage caused by fraudulent disbursements, which is included in the fraud tree of the Association of Certified Fraud Examiners ACFE. To achieve the desired outcomes, a Python application system is developed for this purpose. In the study, an artificial data set containing normal transactions and fraudulent transactions of a bank, was used. Using the Decision Tree technique, which was selected as the chosen method, the main model was developed using a data set with known class labels, and then the model was evaluated using unlabeled data. The model of the decision tree technique achieved 97,1 accuracy, 98,4 f1-score, 98,9 precision and 98 sensitivity. The study is open to improvement in terms of reducing the erroneous class labels produced by the decision tree technique during the estimation phase and can be improved by comparing it with other techniques.

 In the study, it is aimed to contribute to the fraud detection process with an application in which machine learning method is used to reduce the damage caused by fraudulent disbursements, which is included in the fraud tree of the Association of Certified Fraud Examiners ACFE. To achieve the desired outcomes, a Python application system is developed for this purpose. In the study, an artificial data set containing normal transactions and fraudulent transactions of a bank, was used. Using the Decision Tree technique, which was selected as the chosen method, the main model was developed using a data set with known class labels, and then the model was evaluated using unlabeled data. The model of the decision tree technique achieved 97,1 accuracy, 98,4 f1-score, 98,9 precision and 98 sensitivity. The study is open to improvement in terms of reducing the erroneous class labels produced by the decision tree technique during the estimation phase and can be improved by comparing it with other techniques.

 Çalışmada, Sertifikalı Hile Denetçileri Birliğinin ACFE hile ağacında yer alan ve işletmelerde sıklıkla karşılaşılan hileli ödemelerin verdiği zararı azaltmak için makine öğrenmesi yönteminin kullanıldığı bir uygulama ile hile tespit sürecine katkının sağlanması amaçlanmıştır. Bu amaçla, elde edilmek istenen çıktılar için Pythonda bir uygulama sistemi tasarlanmıştır. Çalışmada, bir bankaya ait normal işlemler ile hileli işlemlerin yer aldığı yapay veri setinden yararlanılmıştır. Yöntem olarak kullanılmasına karar verilen Karar Ağacı tekniğiyle önce sınıf etiketleri bilinen bir veri setiyle ana model oluşturulmuş, sonra etiketsiz bir veri seti üzerinde modelin test edilmesi sağlanmıştır. Karar ağacı tekniğinin modeli, 97,1 doğruluk, 98,4 f1-skor, 98,9 kesinlik ve 98 duyarlılık değerlerini elde etmiştir. Çalışma, karar ağacı tekniğinin tahmin aşamasında ürettiği hatalı sınıf etiketlerinin azaltılması açısından iyileştirmeye açık olup, diğer tekniklerle karşılaştırılarak da geliştirilebilir.

Makale detayları

Decision Tree Supported Fraud Detection and an Application

Yazarlar:

Önder Gür

Yayıncı:

Alanya Alaaddin Keykubat Üniversitesi

Ana Başlıklar:

Finans

Dergi:

Alanya Akademik Bakış Vol.7 Issue 1, pp.511-528

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

Türkçe

Document ID (Org No.):

2001283520

pISSN:

2651-4192

Fraud Dedection

Fraudulent

Disbursements

Machine Learning

Decision Tree

Hile Tespiti

Hileli Ödemeler

Makine Öğrenmesi

Kara Ağacı

Sayı

Makale detayları

Yazarlar: Önder Gür

Yayıncı: Alanya Alaaddin Keykubat Üniversitesi

Ana Başlıklar: Finans

Dergi: Alanya Akademik Bakış Vol.7 Issue 1, pp.511-528

Belge Tipi: Makale

Yayın Tarihi: 1/2023

Belge Dili: Türkçe

Document ID (Org No.): 2001283520

pISSN: 2651-4192

Sayı

Yazarlar:

Önder Gür

Yayıncı:

Alanya Alaaddin Keykubat Üniversitesi

Ana Başlıklar:

Finans

Dergi:

Alanya Akademik Bakış Vol.7 Issue 1, pp.511-528

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

Türkçe

Document ID (Org No.):

2001283520

pISSN:

2651-4192