Purpose: The study explores the role of green human capital in the implementation of green logistics practices to build green competitiveness and achieve improved social performance and financial performance.Design/methodology/approach: This study employs structured questionnaires to gather data from 152 managers from manufacturing small and medium enterprises in Ghana. The data are analyzed and the hypotheses are tested using the partial least square structural equation modeling.Findings: The findings reveal that green human capital does have significant influence on financial performance. However, green human capital does not have significant influence on social performance and green competitiveness. Besides, green logistics practices significantly improve social performance, financial performance and green competitiveness. Green logistics practices mediate the relationship between green human capital and green competitiveness, social performance and financial performance. Hence, green human capital influences the successful implementation of green logistics practices, which results in building stronger green competitiveness and better social and financial performances.Originality/value: This paper is among the dearth of studies that examine the role of green human capital in the implementation of sustainable supply chain practices. This study pioneers the exploration of the role of green human capital in the implementation of green logistics practices to improve social performance, financial performance and green competitiveness among manufacturing SMEs in sub-Saharan Africa. Besides, the study's findings expand literature by providing new insights into the effect between green logistics practices, financial performance, social performance and green competitiveness from Ghanaian SMEs.

Stacking, a potent ensemble learning method, leverages a meta-model to harness the strengths of multiple base models, thereby enhancing prediction accuracy. Traditional stacking techniques typically utilize established learning models, such as logistic regression, as the meta-model. This paper introduces a novel approach that integrates computational geometry techniques, specifically solving the maximum weighted rectangle problem, to develop a new meta-model for binary classification. Our method is evaluated on multiple open datasets, with statistical analysis showing its stability and demonstrating improvements in accuracy compared to current state-of-the-art stacking methods with out-of-fold predictions. This new stacking method also boasts two significant advantages: enhanced interpretability and the elimination of hyperparameter tuning for the meta-model, thus increasing its practicality. These merits make our method highly applicable not only in stacking ensemble learning but also in various real-world applications, such as hospital health evaluation scoring and bank credit scoring systems, offering a fresh evaluation perspective.

Decision support for port-city freight gateways is challenging when operational information is limited to aggregated observations and decision indicators are researcher-constructed. This study develops an auditable offline scenario-evaluation framework using 76 monthly Port of Los Angeles observations from January 2020 to April 2026. Five interconnected proxy indices describe drift pressure (APD), information clarity (PED), predictability (GPH), operational learning stability (OLStab), and oscillation severity (GOS). Their algebraic dependence limits regression and pathway tests to internal consistency diagnostics. We evaluate five hypothetical response classes using four tabular reinforcement-learning algorithms, a maintain-release baseline, random actions, and an always-appointment-smoothing rule. A chronological 60-month training and 16-month testing design fits normalization, state thresholds, and reward standardization only on training observations. Across ten random seeds, learned policies reduce test-period proxy GOS by 0.76–1.14% relative to maintaining release; random actions achieve 3.64%, while always smoothing produces a stipulated 10.00% reduction. Fourteen test observations occupy states unseen during training and use a prespecified maintain-release fallback. Since action effects are imposed and subsequent monthly states do not depend on actions, these estimates describe scenario scoring rather than verified operational control. Independent physical validation and action-dependent transition data remain necessary.