Data on global financial statistics demonstrate that total losses from fraudulent transactions around the world are constantly growing. The issue of payment fraud will be exacerbated by the digitalization of economic relations, in particular the introduction by banks of the concept of "Bank-as-a-Service", which will increase the burden on payment services. The aim of this study is to synthesize effective models for detecting fraud in digital payment systems using automated machine learning and Big Data analysis algorithms. Approaches to expanding the information base to detect fraudulent transactions have been proposed and systematized. The choice of performance metrics for building and comparing models has been substantiated. The use of automatic machine learning algorithms has been proposed to resolve the issue, which makes it possible in a short time to go through a large number of variants of models, their ensembles, and input data sets. As a result, our experiments allowed us to obtain the quality of classification based on the AUC metric at the level of 0.977-0.982. This exceeds the effectiveness of the classifiers developed by traditional methods, even as the time spent on the synthesis of the models is much less and measured in hours. The models' ensemble has made it possible to detect up to 85.7 % of fraudulent transactions in the sample. The accuracy of fraud detection is also high (79-85 %). The results of our study confirm the effectiveness of using automatic machine learning algorithms to synthesize fraud detection models in digital payment systems. In this case, efficiency is manifested not only by the resulting classifiers' quality but also by the reduction in the cost of their development, as well as by the high potential of interpretability. Implementing the study results could enable financial institutions to reduce the financial and temporal costs of developing and updating active systems against payment fraud, as well as improve the effectiveness of monitoring financial transactions
The majority of payment solutions in the field of electronic money in Ukraine are implemented on top of card payment systems. At the same time, a number of factors, including the digitization of the economy, orientation towards the European vector of development, the need to counteract the outflow of funds from the country, determine the urgency of developing a competitive national electronic money payment system. The more complex functionality of the electronic money institutions (EMI) determines the more complex structure of the organization of cash flows in the system. At the same time, European legislation clearly regulates the need for the payment system to comply with a number of conditions. In particular, at any moment the sum of balances on all internal wallets of the system must be identical to the balance on the system bank account. The issue of developing a general model of the movement of all types of funds in EMI in real time is still unresolved, which increases the risk of errors at the EMI design stage and ultimately leads to an increase in costs for the full cycle of development of the payment system. The purpose of the article is to develop a model of the movement and distribution of cash flows in the electronic money payment system in real time, which ensures compliance with the conditions of the regulator and the requirements of economic security. The article examines the general structure and main types of payment operations in the electronic money system, derives and substantiates the ratio that determines the liquidity of such a system. The set of basic and auxiliary operations in real modern electronic money systems is considered. A static model for ensuring the integrity of cash flows in electronic payment systems has been built. A model of cash flows in the electronic money system is proposed, which allows considering all basic and technical transactions of the system within one scheme in real time. The proposed model provides accounting of transactions of various types on various electronic wallets, which facilitates not only control over transactions, but also subsequent modernization and adaptation of the system to changing market needs.
КОНЦЕПТУАЛЬНІ ПЕРЕДУМОВИ ІНФОРМАЦІЙНО-АНАЛІТИЧНОГО ЗАБЕЗПЕЧЕННЯ ЕКОНОМІЧНОЇ БЕЗПЕКИ ЕЛЕКТРОННИХ ПЛАТІЖНИХ СИСТЕМАнотація. Електронні платіжні системи стали невід'ємною частиною життя людей у всьому світі, завдяки їх простоті та зручності. Вони дозволяють здійснювати платежі у будь-який час доби, незалежно від місцезнаходження, без необхідності відвідувати банк або обмінювати готівку. Для забезпечення безпеки платежів, використовуються передові технології шифрування та авторизації. Обсяг платіжних операцій у всьому світі постійно зростає.Однак, разом із збільшенням обсягів платіжних операцій, зростає важливість і актуальність проблем, пов'язаних із їх здійсненням. На першому місці серед цих проблем знаходиться платіжне шахрайство, але збільшення масштабів діяльності виявляє й інші вузькі місця, пов'язані із забезпеченням надійної і безперервної роботи програмно-апаратного комплексу платіжних систем, обробкою нестандартних ситуацій, виконанням вимог платіжних регуляторів. Це визначає економічну безпеку електронних платіжних систем.В статті визначено основні завдання економічної безпеки на різних рівнях взаємодії платіжних установ із зовнішніми системами. На рівні взаємодії із клієнтами цезахист платежів та рахунків клієнтів платіжної системи від несанкціонованих транзакцій. На рівні взаємодії із іншими платіжними установами ценадійне виконання основних функцій платіжної системиздійснення переказів коштів. На рівні взаємодії із органами зовнішнього контролю цедотримання законодавства та нормативних обмежень діяльності.
A. Mints, P. Sidelov. Analysis of the global level of the banking system readiness for the implementation of the open banking concept. This research main goal is to give an a vision of current state of Electronic Banking with analysis of the modern state of Open Banking and Open application programming interface (API) initiative. The tectonic shifts in regulation from Central banks and governments digitalisation strategy required from financial institutions to became more technologically ready to comply with licensing. This face banks and financial institutions with a new type of technological challenges which recently wasn't part of regular banks routine and now banks should adopt. Different regions and countries have own regulations and strategies how banking and payments sector should adopt. For example, in Europe each bank must apply a numbers of new software services which was never available for third party companies before. It gives a boost to overall banking and payments software industry to meet the demand of the market. Many other developed countries also have own initiatives for the banking sector similar to PSD2 but with own perspective, timing for implementation and features lists. Standardization and unifications of API's and messaging between financial organization represented in ISO 20022 and main browsers integrated payments API also a huge step forward for integrators, service providers and software development teams. The results of this research represent current stage of readiness of banking and payment industry to new regulations requirements. Banks and Financial institutions must dramatically change their current business model and initiate completely new departments which makes bank more open from technological point of as never before. World wide size companies and organizations promote new financial messaging standards and API implementation on browser levels. With all of this, banks will become more "digital friendly" and new products and services from third party companies, in collaboration with banks, will fill in the market. Inside this research discovered different aspects of the current problems which banks usually faced during implementation and conclusions what they need to expect when such projects is initiated. The information inside this research gives readers detailed information about the most important aspects of the technical side of implementation and review of new standards and tools. Мінц О. Ю., Сідельов П. А. Аналіз глобального рівня готовності банківської системи до імплементації концепції «open banking». Мета даного дослідженняскласти уявлення про поточний стан електронного банкінгу в розрізі концепції Open Banking і відкритого інтерфейсу прикладного програмування (API). Перехід до стратегій цифровізації зажадав від фінансових установ впровадження нових технологій. На шляху до цього банки і фінансові установи зіткнулися з новим типом технологічних проблем, які не мали аналогів раніше. Різні регіони і країни розробляють власні правила і стратегії «open banking». Наприк...
This research explores gross losses from payment card fraud worldwide and considers the main modern fraud methods. The issue of payment fraud will be exacerbated by the digitalization of economic relations, in particular the introduction by banks of the concept of "Bank-as-a-Service", which will increase the burden on payment services.The goal of this research is to highlight and classify main vectors of the deepfakes fraudulent attacks for payment systems in contemporary economy.The methodological basis of the research is general and specific scientific techniques and methods. In particular, a systematic approach, a method of analysis and synthesis, taxonomy, financial technologies, anti-fraud methods.The results of our study confirm that new ways of payment fraud are constantly emerging. The development of anti-fraud methods takes a lot of resources, but it allows us to maintain the credibility of banks and payment organizations and reducing losses from fraud.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.