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.

This paper constructs a new index for measuring de jure central bank independence, the first entirely new index in three decades. The index draws on a comprehensive dataset from the IMF’s Central Bank Legislation Database (CBLD) and Monetary Operations and Instruments Database (MOID) and weightings derived from a survey of 87 respondents, mostly consisting of central bank governors and general counsels. It improves upon existing indices including the Cukierman, Webb, and Neyapti (CWN) index, which has been the de facto standard for measuring central bank independence since 1992, as well as recent extensions by Garriga (2016) and Romelli (2022). For example, it includes areas absent from the CWN index, such as board composition, financial independence, and budgetary independence. It treats dimensions such as the status of the chief executive as composite metrics to prevent overstating the independence of statutory schemes. It distills ten key metrics, simplifying current frameworks that now include upwards of forty distinct variables. And it replaces the subjective weighting systems relied on in the existing literature with an empirically grounded alternative. This paper presents the key features of the new index; a companion, forthcoming paper will provide detailed findings by country/region, income level, and exchange rate regime.