A machine learning–driven framework for Quality 4.0 maturity assessment in service organizations: a socio-technical systems approach to digital quality transformation

Purpose This research aims to develop and validate a comprehensive machine learning (ML)-driven Quality 4.0 maturity assessment framework for service organizations grounded in Socio-Technical Systems (STS) theory. Design/methodology/approach An STS-integrated framework comprising 18 Quality 4.0 dimensions across People, Process, and Technology subsystems was developed through systematic literature synthesis and expert validation. Survey data were collected from 285 service organizations and analysed using Latent Class Analysis to empirically derive five maturity levels. Six supervised machine learning algorithms were evaluated, with the Random Forest classifier achieving the highest predictive performance (accuracy = 0.963). Model interpretability was ensured using SHAP (Shapley Additive Explanations) to quantify the relative importance of individual maturity dimensions. Findings The ML-based model reliably classifies organisations into five empirically derived maturity levels. The SHAP analysis highlights Big Data Analytics, Digital Quality Management, and Technology Integration as the strongest predictive signals for Quality 4.0 maturity classification. The empirical results show that 41% of service organizations operate at a Basic Quality level, whereas only 7% demonstrate maturity aligned with Quality 4.0 excellence. Practical implications Managers can use an ML-driven model to assess their current Quality 4.0 maturity, identify critical improvement areas, and prioritize investments in AI, digital quality management, cultural readiness, and capability development. The model's explainable ML outputs also support evidence-based decision-making and clearer alignment between technological adoption and organizational development. Originality/value This study introduces an empirically grounded, socio-technical, and explainable ML based Quality 4.0 maturity assessment framework tailored to service organizations in a developing economy context. By combining Latent Class Analysis with interpretable machine learning, the framework advances both methodological rigor and practical transparency in maturity assessment.