What drives central bank digital currency implementation? A machine-learning analysis using support vector machines and SHAP explainability

  • 9 Views
  • 0 Downloads

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License

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.

view full abstract hide full abstract
    • Figure 1. Parameter grid for selecting optimal hyperparameters of the Support Vector Classifier model
    • Figure 2. Distribution of values of the dependent variable (y) by classes before balancing
    • Figure 3. Distribution of values of the dependent variable (y) by classes after balancing by the ADASYN method
    • Figure 4. SHAP Summary Plot for the support vector model (SVM)
    • Table 1. Variables of the initial dataset
    • Table 2. Descriptive statistics of the variables in the dataset
    • Table 3. Classification results of the support vector machine model for the test dataset
    • Conceptualization
      Zhanat Khishauyeva, Diana Sitenko, Vitaliia Koibichuk, Arsen Petrosyan, Gaukhar Kodasheva, Ekaterina Dmitrieva, Kseniіa Mohylna
    • Funding acquisition
      Zhanat Khishauyeva
    • Writing – original draft
      Zhanat Khishauyeva, Diana Sitenko, Vitaliia Koibichuk, Arsen Petrosyan, Gaukhar Kodasheva, Kseniіa Mohylna
    • Writing – review & editing
      Zhanat Khishauyeva, Diana Sitenko, Vitaliia Koibichuk, Arsen Petrosyan, Gaukhar Kodasheva, Ekaterina Dmitrieva, Kseniіa Mohylna
    • Visualization
      Diana Sitenko, Vitaliia Koibichuk, Ekaterina Dmitrieva
    • Data curation
      Vitaliia Koibichuk, Kseniіa Mohylna
    • Formal Analysis
      Vitaliia Koibichuk, Ekaterina Dmitrieva, Kseniіa Mohylna
    • Investigation
      Vitaliia Koibichuk, Kseniіa Mohylna
    • Methodology
      Vitaliia Koibichuk, Kseniіa Mohylna
    • Project administration
      Vitaliia Koibichuk
    • Software
      Vitaliia Koibichuk, Gaukhar Kodasheva, Kseniіa Mohylna
    • Supervision
      Vitaliia Koibichuk, Kseniіa Mohylna
    • Validation
      Vitaliia Koibichuk, Ekaterina Dmitrieva, Kseniіa Mohylna
    • Resources
      Arsen Petrosyan