Integrating Expert Prioritisation and Explainable Machine Learning to Evaluate MSME Digital Transformation Readiness

Micro, small, and medium-sized enterprises (MSMEs) increasingly adopt digital technologies, yet converting this exposure into enterprise performance (ENP) requires multidimensional readiness capabilities. Evaluating these capabilities remains complex as existing studies often separate expert judgement, measurement validation, linear association, and explainable prediction. This study therefore develops an integrated analytical framework comprising two sequential phases. First, 22 experts contextualised the seven capability domains through a three-round Delphi process, followed by fuzzy TOPSIS to derive priorities under linguistic uncertainty. Second, cross-sectional survey data from a non-probability convenience sample of 610 eligible MSME respondents in Thailand underwent Confirmatory Factor Analysis (CFA) to validate the measurement structure, followed by hierarchical regression to establish a conventional baseline of adjusted linear associations. Within the second phase, eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) were subsequently applied for internal out-of-sample evaluation and model interpretation. The findings show that experts assigned the highest priorities to digital financial services and digital financial access. The XGBoost model achieved a test R2 of 0.6303, compared with 0.6282 for the OLS benchmark, indicating only a modest predictive improvement. Test-set SHAP identified social media use (mean |SHAP| = 0.2027), adaptive financial resilience, and financial management practice as the leading group of capability-level predictive contributors. The evidence is observational and does not support causal inference. This study contributes an integrated, measurement-validated, explainable framework for capability assessment. Expert-based priorities and SHAP-based predictive contributions provide complementary rather than equivalent forms of evidence.