Araştırma Makalesi
BibTex RIS Kaynak Göster

Artificial Intelligence Based Customer Risk Classification for Receivables Management of Businesses

Yıl 2024, Cilt: 4 Sayı: 2, 97 - 103, 27.12.2024

Öz

This study is carried out with the aim of developing and implementing artificial intelligence-based receivables management systems for businesses. A model is created to predict customers' debt payment situations. In the study, invoice data of a company named QF_CARIRAPOR is utilized. The features table is created in Apache druid and risk scoring label is made manually according to set rules. Then, various machine learning models such as XGBoost, Random Forest are implemented on MindsDB platform. The classified risk score is visualized with the Streamlit user interface using the results created in MindsDB. Among the applied models, XGBoost has resulted in the highest classification accuracy of 98.8 %. The findings reveal the potential to increase the effectiveness of receivables management processes by applying machine learning models.

Kaynakça

  • H.Lam, “Analyzing the Measures of Credit Risk on Financial Corporation and It’s Impact on Profitability,” International Journal of Research in Vocational Studies (IJRVOCAS), vol. 3, no. 1, pp. 64-70, 2023.
  • N. Wilson, B. Summers, R. Hope, “Using payment behaviour data for credit risk modelling,” International Journal of the Economics of Business; vol. 7, no. 3, pp. 33-346, 2000.
  • J. Reyes, J. Perez, and S. Ake, “Credit risk management analysis: An application of fuzzy theory to forecast the probability of default in a financial institution,” Contaduría y Administración, vol. 69, no. 1, pp. 18 211, 2024.
  • A. Markov, Z. Seleznyova, and V. Lapshin, “Credit scoring methods: Latest trends and points to consider,” The Journal of Finance and Data Science, vol. 8, pp. 180-201, 2022.
  • X. Dastile, T. Celik, and M. Potsane, “Statistical and machine learning models in credit scoring: A systematic literature survey,” Applied Soft Computingt, vol. 91, 106263, 2000.
  • Q. Zhou, “Predicting Systemic Risk in Financial Markets Using Machine Learning,” Transactions on Economics Business and Management Research vol. 8, pp. 455-460, 2024.
  • K. Xu, Y. Wu, Z. Li, R. Zhang, and Z. Feng, “Investigating Financial Risk Behavior Prediction Using Deep Learning and Big Data,” International Journal of Innovative Research in Engineering and Management (IJIREM), vol. 11, no. 3,pp. 77-81, 2024.
  • Scikit-learn Machine Learning in Python, https://scikit-learn.org
  • https://druid.apache.org
  • MindsDB-Platform for Building AI, https://docs.mindsdb.com
  • https://streamlit.io

İşletmelerin Alacak Yönetiminde Yapay Zeka Tabanlı Müşteri Risk Sınıflandırması

Yıl 2024, Cilt: 4 Sayı: 2, 97 - 103, 27.12.2024

Öz

Bu çalışma, işletmeler için yapay zeka tabanlı alacak yönetim sistemleri geliştirmek ve uygulamak amacıyla gerçekleştirilmiştir. Müşterilerin borç ödeme durumlarını tahmin etmek için bir model oluşturulmuştur. Çalışmada QF_CARIRAPOR adlı bir şirketin fatura verilerinden yararlanılmıştır. Özellikler tablosu Apache druid'de oluşturulmuş ve risk puanlama etiketi belirlenen kurallara göre manuel olarak yapılmıştır. Daha sonra MindsDB platformunda XGBoost, Random Forest gibi çeşitli makine öğrenimi modelleri uygulanmıştır. Sınıflandırılmış risk puanı, MindsDB'de oluşturulan sonuçlar kullanılarak Streamlit kullanıcı arayüzü ile görselleştirilmiştir. Uygulanan modeller arasında XGBoost, %98 ile en yüksek sınıflandırma doğruluğunu sağlamıştır. Bulgular, makine öğrenimi modellerinin uygulanmasıyla alacak yönetimi süreçlerinin etkinliğini artırma potansiyelini ortaya koymaktadır.

Kaynakça

  • H.Lam, “Analyzing the Measures of Credit Risk on Financial Corporation and It’s Impact on Profitability,” International Journal of Research in Vocational Studies (IJRVOCAS), vol. 3, no. 1, pp. 64-70, 2023.
  • N. Wilson, B. Summers, R. Hope, “Using payment behaviour data for credit risk modelling,” International Journal of the Economics of Business; vol. 7, no. 3, pp. 33-346, 2000.
  • J. Reyes, J. Perez, and S. Ake, “Credit risk management analysis: An application of fuzzy theory to forecast the probability of default in a financial institution,” Contaduría y Administración, vol. 69, no. 1, pp. 18 211, 2024.
  • A. Markov, Z. Seleznyova, and V. Lapshin, “Credit scoring methods: Latest trends and points to consider,” The Journal of Finance and Data Science, vol. 8, pp. 180-201, 2022.
  • X. Dastile, T. Celik, and M. Potsane, “Statistical and machine learning models in credit scoring: A systematic literature survey,” Applied Soft Computingt, vol. 91, 106263, 2000.
  • Q. Zhou, “Predicting Systemic Risk in Financial Markets Using Machine Learning,” Transactions on Economics Business and Management Research vol. 8, pp. 455-460, 2024.
  • K. Xu, Y. Wu, Z. Li, R. Zhang, and Z. Feng, “Investigating Financial Risk Behavior Prediction Using Deep Learning and Big Data,” International Journal of Innovative Research in Engineering and Management (IJIREM), vol. 11, no. 3,pp. 77-81, 2024.
  • Scikit-learn Machine Learning in Python, https://scikit-learn.org
  • https://druid.apache.org
  • MindsDB-Platform for Building AI, https://docs.mindsdb.com
  • https://streamlit.io
Toplam 11 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Makine Öğrenme (Diğer)
Bölüm Research Articles
Yazarlar

Şaban Can Tiryaki Bu kişi benim 0009-0006-2765-5551

Adnan Kavak 0000-0001-5694-8042

Yayımlanma Tarihi 27 Aralık 2024
Gönderilme Tarihi 30 Kasım 2024
Kabul Tarihi 16 Aralık 2024
Yayımlandığı Sayı Yıl 2024 Cilt: 4 Sayı: 2

Kaynak Göster

IEEE Ş. C. Tiryaki ve A. Kavak, “Artificial Intelligence Based Customer Risk Classification for Receivables Management of Businesses”, Journal of Artificial Intelligence and Data Science, c. 4, sy. 2, ss. 97–103, 2024.

All articles published by JAIDA are licensed under a Creative Commons Attribution 4.0 International License.

88x31.png