INTELLIGENT PROCESS ANALYSIS BASED ON ARTIFICIAL INTELLIGENCE AND LOW-CODE PLATFORMS

Abstract

The rapid development of artificial intelligence (AI), machine learning, process mining, and low-code development platforms is transforming the methods used to analyze and optimize organizational processes. Traditional process analysis generally depends on manually constructed process models, expert knowledge, and retrospective examination of operational indicators. By contrast, intelligent process analysis combines event-log data, artificial intelligence algorithms, process mining techniques, predictive analytics, and visual low-code environments to support automated discovery, diagnosis, prediction, and improvement of business processes. This article examines the conceptual and technological foundations of intelligent process analysis based on AI and low-code platforms. The research is based on a structured analysis of scientific literature, systematic reviews, established process-mining research, artificial intelligence governance frameworks, and contemporary studies of low-code development. Particular attention is given to process discovery, conformance checking, predictive process monitoring, machine learning, explainable artificial intelligence, automated machine learning, and human-centered AI. The analysis demonstrates that low-code platforms can reduce the technical barrier to implementing AI-supported process-analysis solutions by providing visual modeling, reusable components, integration mechanisms, and automated workflows. However, low-code environments do not eliminate fundamental requirements concerning data quality, model validation, security, explainability, governance, and human oversight. Recent systematic research also indicates that the benefits of low-code development are context-dependent and that security, complexity, and governance remain important challenges. The article proposes an integrated conceptual architecture in which low-code platforms function as the implementation and orchestration layer, while AI and process-mining technologies provide analytical intelligence. Such an approach can contribute to faster process diagnosis, predictive decision support, continuous monitoring, and evidence-based process improvement.