An Approach to Business Workflow Software Architectures: A Case Study for Bank Account Transaction Type Prediction


Çallı F. G., Ayyıldız Ç., Açıkgöz B. K., AKTAŞ M. S.

22nd International Conference on Computational Science and Its Applications , ICCSA 2022, Malaga, İspanya, 4 - 07 Temmuz 2022, cilt.13381 LNCS, ss.709-723 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 13381 LNCS
  • Doi Numarası: 10.1007/978-3-031-10548-7_51
  • Basıldığı Şehir: Malaga
  • Basıldığı Ülke: İspanya
  • Sayfa Sayıları: ss.709-723
  • Anahtar Kelimeler: Association mining rules, Deep learning, Electronic bank transaction categorization, Electronic bank transaction prediction, FP-Growth, LSTM, Machine learning
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

Today, practically every bank’s computer system can automatically categorize transactions. If someone uses their debit/credit card to buy groceries or clothing, they can see the sort of expense on their user account in seconds. Even though banks provide this level of categorization for individual users, there is no categorization solution for accounting systems. In this article, the main objective is to design and develop a business workflow that can predict bank account transaction types. Various machine learning and deep learning algorithms are used to accomplish this purpose. In the prototype implementation, Support Vector Machines, Random Forest, Long Short-Term Memory Networks, and Frequent Pattern Growth algorithms are used, and the prediction successes of these techniques are analyzed.