Intelligent Workflow Orchestration Using Low-Code BPM Platforms and Machine Learning: Automating Lending Operations in Member-Centric Financial Institutions
Main Article Content
Abstract
The rapid evolution of digital transformation in financial services has led to the convergence of low-code Business Process Management (BPM) platforms and machine learning (ML) technologies. This convergence enables intelligent workflow orchestration, particularly in complex, regulated domains such as lending operations. This paper investigates how low-code BPM platforms— exemplified by PEGA-style case management systems—can be augmented with ML-driven decision-making to automate lending processes in member-centric financial institutions. The study explores architectural patterns, integration strategies, and measurable outcomes such as efficiency gains, error reduction, and return on investment (ROI). Furthermore, it examines the role of human-in-theloop (HITL) design in ensuring compliance, transparency, and ethical governance. Drawing upon existing literature and industry practices, this work proposes a generalized framework for intelligent lending automation and identifies future research directions in hyperautomation and adaptive workflow systems.