Corporate social responsibility and profitability in Islamic insurance firms: insights from explainable AI

Purpose This study aims to examine how corporate social responsibility (CSR) influences Takaful (Islamic insurance) insurers’ financial performance, with an additional emphasis on the moderating role of Shariah governance. Design/methodology/approach Drawing on a sample of 33 Takaful companies over a five-year period (2018–2022), the authors use an explainable artificial intelligence framework that integrates eXtreme Gradient Boosting and SHapley Additive exPlanations (SHAP). Findings CSR exhibits a modest direct effect on profitability, but gains added significance when paired with strong Shariah governance. SHAP-based dependence plots also reveal nonlinear patterns in the CSR–performance relationship, suggesting that higher or lower levels of CSR may yield more pronounced effects than moderate levels. Robustness checks using return on equity confirm these insights, indicating consistent dynamics across alternative performance measures. Originality/value By combining advanced machine learning with SHAP-based interpretative analysis, this paper provides insights into how CSR and governance together influence financial performance.