Decision Support Systems facilitate timely and informed decision-making by integrating heterogeneous data sources, analytical models, and user interfaces into cohesive systems. This study introduces a general-purpose and scalable Decision Support System framework that supports just-in-time, data-driven decision-making processes across diverse application domains. The proposed system architecture incorporates essential technologies, including Apache Kafka for parallel data streaming, a Python-based distributed data analytics module, a role-based access control system for authentication and authorization, and a WebSocket interface to deliver predictions in real-time. The Iris dataset was utilized for model validation, with logistic regression employed as the predictive model. Experimental evaluations were conducted under simulated load conditions using the Artillery tool to assess system scalability and responsiveness. Results demonstrate significant performance improvements when utilizing Apache Kafka consumer group with associated worker modules for parallel processing, achieving lower mean, median, P95, and P99 latencies. These findings highlight the effectiveness of the proposed architecture in enabling highly scalable and responsive Decision Support System applications that support just-in-time decision-making.
Öztel et al. (Thu,) studied this question.