The use of ML algorithms in the task of detecting fraud when using plastic cards

T.A. Osipova, K.S. Zaytsev, V.O. Bifert


Today there is a significant increase in the number of incidents involving the use of plastic cards, as well as a variety of fraudulent methods used by cybercriminals. The presented article is devoted to the application of machine learning methods to counter fraudulent transactions using plastic cards. The aim of the article is to study the effectiveness of various machine learning models in the analysis of transactions with plastic cards to identify various types of fraud. The article sequentially analyzes such machine learning methods as RandomForest, CatBoost, LogisticRegression, 2-layer ordinary perceptron and Rumelhart's multilayer perceptrons L-BFGS and SGD. Considerable attention is paid to the process of preparing data for participation in modeling, which is iterative and includes operations for selecting tables, attributes, records, converting, cleaning data, filtering and combining them in the desired format. The dataset was taken from Worldline and the ULB Machine Learning Group for Big Data Mining and Fraud Detection. The problem with class imbalance was solved using resampling. Rumelhart's L-BFGS and SGD perceptrons showed the best results in experiments when using the metrics "response time" and "accuracy".

Full Text:

PDF (Russian)


Tadviser [online resource] //Bank card fraud [website] URL: Article: Bank Card Fraud (Date of request 23.10.2020)

HABR [online resource] // Machine learning algorithms [website] URL: (Date of request 6.12.2020)

KPFU [online resource] // Artificial neural networks and their applications [website] URL: (Date of request 4.04.2021)

Apmonitor [online resource] // Deep Learning [website] URL: (Date of request 2.04.2021)

Python-school [online resource] // TensorFlow vs PyTorch: What and When to Choose for Machine Learning [website] URL: ( Date of request 20.03.2021)

Kaggle [online resource] // [website] ( Date of request 17.10.2020)

Kaggle [online resource] // [website] (Date of request 10.10.2020)

Neural-university [online resource] // What are neural networks [website] URL: (Date of request 10.04.2021)

"A literature survey on Machine Learning Algorithms", International Journal of Emerging Technologies and Innovative Research (, ISSN:2349-5162, Vol.6, Issue 4, page no.471-474, April-2019, Available :

Machine learning approach to literature mining for the genetics of complex diseases, Jessica Schuster, Michael Superdock, Anthony Agudelo, Paul Stey, James Padbury, Indra Neil Sarkar, Alper Uzun, Author Notes, Database, Volume 2019, 2019, baz124. URL:

Fraud [online resource] // Fraud Detection with Machine Learning [website] URL: (Date of request 21.04.2021) [online resource] // Theft with bank cards [website] URL: (Date of request 18.04.2021)

Bazhenov [online resource] // Classifier score (presicion, recall, F-score) [website] URL: (Date of request 16.11.2020)

Machinelearningmastery [online resource] // Dealing with unbalanced data [website] URL: (Date of request 2.12.2020) [online resource] // Prevent false relationships and imbalanced data through automated machine learning [website] URL: (Date of request 2.04.2021) [online resource] // Neural networks in anti-fraud modeling [website] URL: (Date of request 12.04.2021)

mql5 [online resource] Gradient boosting [website] URL: (Date of request 7.12.2020)

AI-news [online resource] // Big data [website] URL: (Date of request 26.05.2021)

AI-news [online resource] // Problems and errors of machine learning, neural networks / big data [website] URL: (Date of request 26.05.2021)

AI-news [online resource] // Neural network news: who is Prover-7 and why sample quality is more important than sample size [website] URL: (Date of request 27.05.2021) [online resource] // ReLU: Not a Differentiable Function [website] URL: (Date of request 13.04.2021)

Arefyevstudio [online resource] // What is resampling? [website] (Date of request 20.03.2021)


  • There are currently no refbacks.

Abava  Absolutech Convergent 2020

ISSN: 2307-8162