Independent boards win: How independent board members drive financial success in hospitality and tourism firms

Abstract

This study examines the influence of board composition and Environmental, Social, and Governance (ESG) practices on financial performance within the hospitality and tourism industry, leveraging advanced machine learning techniques. Data spanning 2015–2024 from the Refinitiv database is analyzed through boosting algorithms, SHapley Additive exPlanations (SHAP), and Partial Dependence Plots (PDPs) to uncover nonlinear interactions and relative predictor importance. The findings emphasize that Independent Board Members Score (IBMS) consistently drives financial performance across metrics, while Non-Executive Board Members Score (NEBMS) provides complementary support, particularly in interaction with IBMS. ESG variables, including Workforce Score and Product Responsibility Score, emerge as critical predictors, underscoring the importance of sustainability and governance practices. The results validate agency and resource dependence theories, incorporating ESG dimensions and demonstrating the utility of machine learning for governance-performance analyses. It contributes to the theoretical and practical understanding of governance mechanisms, providing a robust framework for achieving competitive financial outcomes in dynamic and sustainability-focused industries.