Dalibor Pudić

The accelerating energy transition and growing geopolitical uncertainty have strengthened the strategic importance of hydrogen within future low-carbon energy systems. Green hydrogen is increasingly recognized as a key energy carrier supporting industrial decarbonization, renewable energy integration, long-term energy storage and energy security. However, existing hydrogen market assessment approaches remain fragmented and frequently focus on isolated technological, regulatory, or investment-related dimensions without sufficiently integrating the systemic interactions that shape hydrogen market maturity. To address this research gap, this study proposes the Integrated Green Hydrogen Market Development Index (IGHMDI), a multidimensional composite indicator framework designed to evaluate hydrogen market development through the integration of regulatory, technological, infrastructural, financial and strategic dimensions. This methodological framework is based on established principles of composite indicator construction, including indicator selection, normalization, weighting, and aggregation procedures adapted to the characteristics of emerging hydrogen markets. The proposed framework incorporates six principal dimensions: regulatory and policy development, technological readiness, infrastructure and market integration, investment and financial readiness, market demand and industrial adoption, and international cooperation and strategic positioning. An illustrative pilot application comparing Croatia and Germany is used to demonstrate the operational logic of the framework and its ability to distinguish between hydrogen markets at different stages of development. The illustrative assessment produced composite IGHMDI scores of 65.0 for Croatia and 91.7 for Germany, demonstrating the framework’s capability to distinguish hydrogen markets at different stages of structural development while providing a transparent basis for comparative assessment. The results indicate that hydrogen market development increasingly depends on the interaction between regulatory stability, infrastructure readiness, technological innovation, investment support mechanisms, market demand, and international coordination. The study also acknowledges that broader empirical validation, sensitivity analysis, and longitudinal application across a larger set of countries are required in future research. Overall, the IGHMDI framework contributes to the development of multidimensional hydrogen market assessment methodologies and provides a transparent analytical tool for comparative benchmarking, policy evaluation, infrastructure prioritization, and future hydrogen transition governance.

Predicting innovation outcomes at the firm level continues to be an important but challenging goal for researchers and practitioners alike. In this study, multiple machine learning models, encompassing both ensemble-based and single-model approaches, were applied to data from the Community Innovation Survey. Methods included random forests, gradient boosting frameworks, support vector machines, neural networks, and logistic regression, each with hyperparameters optimized through Bayesian search routines and evaluated using corrected cross-validation techniques. The results showed that tree-based boosting algorithms consistently outperformed other models in accuracy, precision, F1-score, and ROC-AUC, while the kernel-based approach excelled in recall. Logistic regression proved to be the most computationally efficient model despite its weaker predictive power. The statistical analyses made it clear that the choice of an appropriate cross-validation protocol and accounting for overlapping data splits are crucial to reduce bias and ensure reliable comparisons. Overall, the results indicate that ensemble methods generally provide robust classification performance for innovation prediction tasks. However, individual models may still prove advantageous under certain metric-specific conditions or computational constraints. These observations emphasize the need to match model selection with data structure, performance objectives, and practical resource constraints when predicting and improving innovation outcomes at the firm level.