This study proposes a multi-objective, multi-class explainable modeling framework to explain country performance profiles in PISA Mathematics (PISAM), Reading (PISAR), and Science (PISAS). Instead of treating PISA as a simple ranking, the study models each country’s Low/Medium/High-achieving class and asks which structural signals the model relies on when assigning a country to this class. To this end, the study combines governance quality (e.g., accountability, control of corruption, and political stability, etc.), economic and administrative capacity, and regional/institutional location in a single prediction pipeline and explains the resulting classifications with SHAP contributions conditional on class. While the findings do not point to a single, universal determinant, in mathematics, high-level profiles cluster around political stability, economic scale barriers, and regional location, along with governance indicators; in reading, economic capacity is explicitly integrated into this institutional core; and in science, in addition to these two dimensions, the shared institutional dynamics of regional blocs come into play. Furthermore, the study not only produces explanations but also quantitatively reports their reliability. The fit with the model output (Fidelity) and the traceability of the decision logic (Faithfulness) are 0.95/0.85 for PISAM, 0.89/0.92 for PISAR, and 0.89/0.89 for PISAS, which demonstrates high internal consistency and traceability of the decision process. Overall, the study reframes the PISA results not as isolated test scores but as structural profiles generated by the combination of governance, capacity, and region, revealing the policy-relevant levers behind “high performance” as a transparent and reproducible decision-making pipeline. This provides policymakers with an important roadmap for creating a sustainable education policy.

This paper investigates how economic capacity, budget priorities, and governance conditions jointly shape defense spending in a transparent and auditable empirical framework. Using annual cross-country data for 2002–2023 compiled from widely used international sources, we evaluate the relative importance of economic indicators, fiscal allocation patterns, and institutional factors in explaining defense expenditure outcomes. We use Explainable Artificial Intelligence (XAI) to quantify the relative contribution of these factors in a transparent and interpretable manner. The results show that economic capacity and the way governments prioritize defense within overall public finances are the strongest and most consistent drivers of defense spending differences across countries. Governance conditions act as an institutional filter that can constrain or intensify these effects: more democratic and accountable environments tend to limit increases in defense spending, whereas lower political stability is associated with upward spending pressure. These findings are important because they clarify that defense expenditure is not determined by a single factor, but by a layered interaction between resources, priorities, and institutions. The study contributes a replicable and policy-relevant approach for interpreting defense spending dynamics and for supporting accountable decision-making in defense budgeting.

Studies explaining the variation in educational outcomes across countries, when based on “black box” models that provide high accuracy but struggle to present the decision-making mechanism transparently, carry the risk of producing limited interpretations for policy discussions. This study examines the system-level relational patterns through which the subcomponents of the Heritage Foundation Index of Economic Freedom distinguish country-average low–medium–high PISA performance profiles in mathematics, reading, and science, and interprets these patterns using machine learning and explainable artificial intelligence (XAI). The analysis draws on approximately twenty years of nominal country-year records covering 76 countries. The study design proceeds through a classification approach, treating country performance as low–medium–high profiles; thus, model outputs are presented on an interpretable reference plane for cross-country comparisons. The findings indicate that the models demonstrate consistent generalization ability in distinguishing performance profiles and that the XAI layer produces explanations that make the model’s reasoning visible in a verifiable manner. The explanation results indicate that components representing institutional trust (such as government integrity and property rights) produce strong, recurring signals alongside higher performance profiles in all three areas; while components such as public expenditure and tax burden can emerge as balancing/suppressing signals in some scenarios. Rather than offering causal policy implications, these findings transparently reveal the structural areas that stand out in distinguishing performance profiles in cross-country comparisons, thus providing an explainable, replicable evidence base for comparative analysis and further research.

Explainable artificial intelligence methods are increasingly expected to provide not only interpretable representations but also evidence that their explanations reflect model behavior beyond the data used to construct them. This study introduces ABC-FaithOpt, a model-agnostic global XAI framework that combines stability-aware Artificial Bee Colony feature discovery with constrained optimization of explanation weights. Repeated train-only ABC searches are aggregated to obtain a consensus feature representation and initial weights, which are subsequently refined on calibration perturbations. A separate validation guard controls acceptance of the optimized explanation, while final faithfulness is evaluated on untouched outer-test data using disjoint perturbation masks. The framework was assessed across heterogeneous tabular classification datasets and multiple classifier families and compared with ABC initialization, permutation importance, Monte Carlo SHAP, and native model importance under a common selected-feature space and evaluation protocol. ABC-FaithOpt achieved a mean held-out behavioral reconstruction R2 of 0.910 and showed higher reconstruction performance than the comparison methods under the primary evaluation criterion, including SHAP-MC. Complementary ablation, sensitivity, synthetic, shuffled-label, stability, and conditional-deletion analyses supported the contribution of weight refinement to the observed reconstruction performance, while predictive preservation and feature-selection stability remained dataset dependent. Overall, ABC-FaithOpt provides a compact global explanation framework that combines stability-aware feature discovery with held-out behavioral-faithfulness optimization and evaluation, offering a promising basis for global model auditing and explanation validation in tabular classification settings.