K-Bank "AI Research Paper Published in KCI Indexed Journal"

[Financial News] K-Bank has been recognized by academia for its AI technology research capabilities.
K-Bank announced on the 14th that it has published a paper presenting theoretical grounds for the strategic design and performance of an AI-based personalized recommendation system in the KCI indexed journal of the Korean Data Analysis Society.
The paper is the result of research on the 'personalized' K-Bank app reflecting customer behavior patterns. The paper, titled 'Strategic Design of AI-based Recommendation System and Analysis of User Experience Changes: Financial App Experiment through MLOps Automation', was published in the domestic data analysis journal JKDAS (Journal of the Korean Data Analysis Society). JKDAS is a journal published by the Korean Data Analysis Society (KDAS) that actively deals with theory and application research of statistics-based data analysis and is one of the major domestic journals indexed in the Korean Citation Index (KCI).
This study empirically analyzed the impact of AI technology on customer behavior change, user experience, and corporate profitability, focusing on the personalized recommendation system applied to the K-Bank app. It is evaluated as a meaningful attempt as a study of AI model personalization strategy in the financial sector, not in industries such as commerce or OTT where personal recommendations are active.
In particular, K-Bank conducted FGI targeting various financial sector managers within K-Bank, such as loans and deposits, to design a model optimized for the financial industry. Through this, they accurately identified customer types and behavior patterns and applied the results from the AI model development stage, reflecting the characteristics of financial consumers beyond simple technology-centered recommendations, and improved predictive performance and operational stability.
This recommendation system is implemented based on MLOps to detect and analyze behavioral data such as preferences and dwell time of customers using the app in real-time. A feature of this system is the creation of an automated process that continuously learns from the analysis results and re-applies them to the system.
Meanwhile, K-Bank has accelerated AI financial innovation this year by introducing a private LLM (Large Language Model) to build an AI automation system for internal work efficiency and laying the foundation for expanding customer-facing AI services. In particular, they invested about three times more in AI and cloud compared to last year, including expanding GPU servers.
A K-Bank representative said, "We aim to ultimately develop the system we built based on AI technology into an AI Agent system to provide more sophisticated financial services to customers," and added, "We will continue to focus on leading AI-based financial services and transform into an 'AI Powered Bank'."

mj@fnnews.com Park Moon-su Reporter