Operational Risk Indicators Derived from Customer Interaction Data in Digital Banking Platforms

Digital banking platforms generate large volumes of operational information through transaction processing systems, system logs, and customer communication channels. Many studies examine transaction monitoring, fraud detection, and cybersecurity events. Customer interaction records receive less attention as a source of operational risk information. This study investigates the use of customer interaction data as indicators of operational conditions in digital banking platforms. The research examines interaction records collected from support tickets, complaint submissions, chat conversations, and service request logs. These records are analyzed together with Management Information System (MIS) event logs in order to identify recurring service issues and operational patterns. The proposed analytical framework organizes interaction data through several stages that include data collection, preprocessing, interaction pattern detection, and operational risk indicator generation. Repeated reports related to transaction delays, authentication failures, and application performance problems appear within the interaction dataset. These patterns correspond to operational events recorded in system activity logs. The study also introduces a quantitative operational risk score calculated from the frequency and severity of interaction categories. The results indicate that customer interaction datasets contain measurable signals related to operational disruptions within digital banking platforms. The analytical framework demonstrates that interaction records provide an additional information source for operational monitoring and risk analysis in digital financial services.