Copyright Page

© 2023 International Monetary Fund

WP/23/241

IMF Working Paper

Information Technology Department and Monetary and Capital Markets Department

Predicting the Law: Artificial Intelligence Findings from the IMF’s Central Bank Legislation Database

Prepared by Khaled AlAjmi, Jose Deodoro, Ashraf Khan¹, and Kei Moriya

All authors contributed equally to this work

Authorized for distribution by Bachir Boukherouaa and Jihad Alwazir

November 2023

ABSTRACT:

Using the 2010, 2015, and 2020/2021 datasets of the IMF’s Central Bank Legislation Database (CBLD), we explore artificial intelligence (AI) and machine learning (ML) approaches to analyzing patterns in central bank legislation. Our findings highlight that: (i) a simple Naïve Bayes algorithm can link CBLD search categories with a significant and increasing level of accuracy to specific articles and phrases in articles in laws (i.e., predict search classification); (ii) specific patterns or themes emerge across central bank legislation (most notably, on central bank governance, central bank policy and operations, and central bank stakeholders and transparency); and (iii) other AI/ML approaches yield interesting results, meriting further research.

RECOMMENDED CITATION: Al Ajmi, K., J. Deodoro, A. Khan, K. Moriya, 2023, Predicting the Law: Artificial Intelligence Findings from the IMF’s Central Bank Legislation Database. IMF Working Paper 23/241. Washington, D.C.: International Monetary Fund.

JEL Classification Numbers:	C53, C55
Keywords:	central bank legislation; central banking; artificial intelligence; machine learning; Bayesian algorithm; Boolean algorithm; central bank governance; law and economics
Author’s E-Mail Address:	kalajmi@imf.org; jdeodoro@imf.org; akhan4@imf.org; kmoriya@imf.org

View Table

JEL Classification Numbers:	C53, C55
Keywords:	central bank legislation; central banking; artificial intelligence; machine learning; Bayesian algorithm; Boolean algorithm; central bank governance; law and economics
Author’s E-Mail Address:	kalajmi@imf.org; jdeodoro@imf.org; akhan4@imf.org; kmoriya@imf.org

Title Page

WORKING PAPERS

Predicting the Law

Artificial Intelligence Findings from the IMF’s Central Bank Legislation Database

Prepared by Khaled AlAjmi, Jose Deodoro, Ashraf Khan, and Kei Moriya¹

Contents

• Glossary

• Introduction

• AI/ML Approaches

• User Statistics

• Conclusion

• Annex I. CBLD Coding App

• Annex II. Overview of CBLD Search Categories

• References

• FIGURES

• 1. CBLD Data Coverage 2010/2015, 2020/2021)

• 2. Number of Included Laws (by country)

• 3. CBLD Data Flow

• 4. Example of the Landing Page and a Coding Page of the CBLD Coding App

• 5. Multiplicity of Categories

• 6. Most Relevant Words and Coefficients for Category 1.01

• 7. Fraction of Correct Categories Against Ranking

• 8. Fraction of Correct Categories Against Ranking Across All Categories

• 9. Most Counted Tokenized Words

• 10. Themes of Frequently Occurring Tokenized Words in the CBLD

• 11. Word Network Graph for Common Bigrams (Albania)

• 12. Word Network Graph for Common Bigrams (Italy)

• 13. Word Correlation in Laws for United Kingdom and India

• 14. Proportion of Bigram Combinations on “Independ” and “Autonom” Across Central Bank Legislation

• 15. Coverage of Bigram Cominations of “Independ” and “Autonom” Across Central Bank Legislation

• 16. CBLD External Users: Number of Searches

• 17. CBLD External Users: Regional Coverage (in percent)

• 18. CBLD Daily User Queries (2021, 2022)

• 19. CBLD Daily User Queries by Search Category (2021–2023)

• 20. CBLD Daily User Queries by Country (2021–2023)

• 21. CBLD User Queries by Country (2021–2023)

Glossary