Browsing by Author "Sattarbek A."

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    EXPLORING THE IMPACT OF MACHINE LEARNING ON KYC COMPLIANCE COSTS AND CUSTOMER EXPERIENCE
    (СДУ хабаршысы - 2023, 2023) Sattarbek A. ; Zhumashev B.; Parmanov S.
    Abstract. The Know Your Customer (KYC) compliance process is a critical requirement for financial institutions to prevent money laundering, fraud, and terrorist financing. Machine learning algorithms have the potential to improve the efficiency and accuracy of KYC compliance checks. In this study, we explored the effectiveness of several classification algorithms for KYC compliance checks using a dataset with 3000 rows collected from a famous banking system in Kazakhstan. We compared the performance of four commonly used algorithms: Decision Tree, Random Forest, Logistic Regression, and Support Vector Machines. Our results showed that all four algorithms achieved high accuracy rates, with Random Forest performing the best, achieving an accuracy rate of 92.1%. These findings suggest that machine learning algorithms can effectively classify KYC checks, with Random Forest being the most effective algorithm in our study. This study provides further evidence of the potential of machine learning for KYC compliance checks in the banking industry, but also highlights the need for ongoing monitoring and validation of machine learning models and concerns about explainability and transparency.
  • Thumbnail Image
    ItemOpen Access
    Exploring the Impact of Machine Learning on KYC Compliance Costs and Customer Experience
    (2023) Sattarbek A.
    The financial sector is no exception to how diverse businesses have been transformed by advances in machine learning technologies. This study explores the important subject of how machine learning affects Know Your Customer (KYC) compliance costs and customer experience. For financial institutions to reduce risks, ensure regulatory compliance, and provide a streamlined onboarding experience for consumers, KYC compliance is essential. Machine learning approaches have considerable promise for enhancing efficiency, accuracy, and cost-effectiveness in KYC processes. The importance of KYC compliance is established in the study’s opening section, which also emphasizes the need for effective processes to satisfy regulatory standards and boost client confidence. By demonstrating how machine learning’s ability to automate manual chores, identify fraudulent activity, and improve decision-making processes, it further demonstrates why this field of technology is crucial to investigate in the context of KYC compliance. The existing studies and literature on KYC compliance costs and customer experience are consolidated through an extensive literature review, laying the groundwork for further investigation. The review discusses many aspects of KYC compliance costs, existing norms and issues in the banking industry, as well as the application of machine learning to KYC procedures. The examination into the key components and variations in KYC compliance requirements across jurisdictions and regulatory agencies is then guided by the research objectives and questions of the study, which are then laid forth. The research approach used entails the collecting of data from a reputable banking iv institution in Kazakhstan, which includes a dataset with extensive client information, transaction details, and risk indicators. After gathering the data, it is rigorously analyzed utilizing machine learning algorithms. In the study, the effectiveness of Decision Tree, Random Forest, Logistic Regression, and Support Vector Machines—four widely used classification algorithms—is compared. The prediction skills of these algorithms are evaluated using metrics including accuracy, precision, recall, and F1-score. The study’s conclusions offer insightful information on how machine learning affects customer satisfaction and KYC compliance expenses. They provided evidence of the integrated machine learning model’s efficiency in expediting the KYC procedure, cutting expenses, and improving decision accuracy. The outcomes also emphasize the opportunities and difficulties associated with integrating the model as an iOS SDK, highlighting its potential to enable smooth integration into banking mobile applications. The study also recognizes the significance of current trends and suggested directions for the future. It investigates the incorporation of additional AI techniques to strengthen the KYC procedure and boost user experience, such as liveness detection and OCR algorithms. Overall, by offering information about the effects of machine learning on KYC compliance costs and customer experience, this study adds to the body of current knowledge. For financial organizations looking to use machine learning technologies to improve their KYC procedures, the findings have real-world applications.