Predicting the Law: Artificial Intelligence Findings from the IMF’s Central Bank Legislation Database
IMF Working Papers, November 17, 2023
Source details
- Canonical URL
- Predicting the Law: Artificial Intelligence Findings from the IMF’s Central Bank Legislation Database
Other formats
Bibliographic details
- Authors: Khaled AlAjmi, Jose Deodoro, Ashraf Khan, Kei Moriya
- Published: November 17, 2023
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9798400260636.001
Summary
- Using the 2010, 2015, and 2020/2021 datasets of the IMF’s Central Bank Legislation Database (CBLD), the paper explores artificial intelligence (AI) and machine learning (ML) approaches to analyzing patterns in central bank legislation.
- The paper highlights three primary conclusions:
- (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);
- (iii) other AI/ML approaches yield interesting results, meriting further research.
Data and Methods
- Datasets used:
- 2010 dataset
- 2015 dataset
- 2020/2021 dataset
- AI/ML approaches examined:
- Naïve Bayes algorithm (noted for ability to predict search classification)
- Other AI/ML approaches (described as yielding interesting results and meriting further research)
Key Findings
- Predictive classification:
- A simple Naïve Bayes algorithm can link CBLD search categories to specific law articles and phrases with a significant and increasing level of accuracy.
- Emergent patterns and themes across central bank legislation:
- Central bank governance
- Central bank policy and operations
- Central bank stakeholders and transparency
- Further research:
- Other AI/ML approaches produce noteworthy results and warrant additional study.
Subject Areas and Keywords
- Subject: Artificial intelligence, Central bank autonomy, Central bank governance, Central bank legislation, Central bank transparency, Central banks, Technology
- Keywords include: approaches to analyzing pattern, artificial intelligence, Bayesian algorithm, Boolean algorithm, capital markets Department, CBLD data flow, Central bank autonomy, central bank governance, central bank legislation, Central bank transparency, central banking, Global, IMF Central Bank Legislation Database, IMF central bank transparency code, law and economics, machine learning, ML approach
Content in this bundle
- Working Paper