Ekaterina Dmitrieva

Type of the article: Research Article

Abstract
Central bank digital currency (CBDC) programs have rapidly shifted from experimentation to policy-critical infrastructure decisions, yet countries show strikingly uneven progress from research to pilots and implementation. This study aims to identify and explain the key structural, macroeconomic, technological, and ecosystem-related factors that differentiate CBDC initiatives advancing to pilot or implementation stages from those remaining in early research or being discontinued across countries worldwide. Using 161 CBDC projects across 109 countries (as of December 2024) and 10 project-, public interest-, technology-, and macroeconomic indicators, we estimate a Support Vector Machines classifier with GridSearchCV (5-fold) tuning and interpret the results using Shapley Additive exPlanations explainability. The raw outcome distribution was strongly imbalanced (83.85% in the early/cancelled class), so ADASYN balancing was applied, producing 270 observations with equal class shares and an 85/15 train–test split (229/41). The optimized SVM (RBF; C = 10, gamma = 10) achieved 93.90% cross-validated accuracy and 0.88 accuracy on the test set, indicating strong predictive performance on unseen data. Test-set metrics show an informative error profile: for class 1 (advanced projects), recall = 1.00 and F1 = 0.89, while for class 0 (early/cancelled), precision = 1.00 with recall = 0.75 (macro/weighted F1 = 0.88), implying that the model identifies all advanced projects but may misclassify around one-quarter of early/cancelled cases. SHAP ranks the strongest drivers as use-case direction, inflation, crypto adoption ranking, CBDC-related research output, and international participation, with mixed/wholesale projects, higher inflation, stronger scientific attention, and greater international involvement generally increasing the likelihood of advancement.

Type of the article: Research Article

Abstract
Money laundering threatens global financial integrity, while digital governance is increasingly seen as a tool to enhance transparency and regulatory capacity. This study operationalized digital governance through the United Nations E-Government Development Index, which captures the scope and quality of online public services, telecommunications infrastructure, and human capital. The paper aims to examine whether improvements in e-government development are associated with measurable reductions in systemic money-laundering vulnerabilities at the country level. The study uses an unbalanced panel of 171 countries for 2012–2024 (982 observations). Fixed- and random-effects models with Box–Cox transformations were estimated, with the Hausman test guiding model selection and cluster-robust and Driscoll–Kraay standard errors ensuring reliable inference. The results demonstrate a statistically significant and economically meaningful inverse relationship between e-government development and money-laundering risk, measured by the Basel AML Index. In the preferred fixed-effects specification, the coefficient on the transformed EGDI is –1.56 (p < 0.001), indicating that within-country improvements in digital governance capacity are associated with substantial reductions in AML vulnerability over time. This effect remains robust across alternative error structures, with 95% confidence intervals of [–1.96, –1.17] under cluster-robust estimation and [–1.75, –1.38] under Driscoll–Kraay correction. The inclusion of country-specific fixed effects reveals considerable structural heterogeneity in baseline AML risk (approximately 1.15–3.90), while time effects display limited variation over the sample period (approximately 2.11–2.19), confirming that the risk-reducing role of digital governance is not driven by specific countries or particular years.

Acknowledgment
This article was prepared based on the results of a study funded by the Ministry of Education and Science of Ukraine, “GovTech for Ukraine: A Digital, Secure, Transparent, and Equitable State in Times of War and Post-War Reconstruction” (registration number: 0126U000544).