Learning to Regulate: A New Event-Level Dataset of Capital Control Measures

TL;DR

This paper introduces a comprehensive event-level dataset of capital control measures from 196 countries (1999-2023), utilizing large language models for extraction and classification, enabling detailed policy analysis and cross-country comparisons.

Contribution

It presents a novel dataset and a framework using LLMs for automated extraction and classification of capital control events, advancing empirical economic research tools.

Findings

Inward capital controls reduce fund inflows within one month.

Restrictive policies have stronger effects than liberalizing ones.

Heterogeneity in policy impacts across countries.

Abstract

We construct a novel event-level Capital Control Measures (CCM) dataset covering 196 countries from 1999 to 2023 by leveraging prompt-based large language models (LLMs). The dataset enables event study analysis and cross-country comparisons based on rich policy attributes, including action type, intensity, direction, implementing entity, and other multidimensional characteristics. Using a two-step prompt framework with GPT-4.1, we extract structured information from the IMF's Annual Report on Exchange Arrangements and Exchange Restrictions (AREAER), resulting in 5,198 capital control events with 27 annotated fields and corresponding model reasoning. Secondly, to facilitate real-time classification and extension to external sources, we fine-tune an open-source Meta Llama 3.1-8B model, named CCM-Llama, trained on AREAER change logs and final status reports. The model achieves 90.09\% accuracy in category classification and 99.55\% in status prediction. Finally, we apply the CCM dataset in an empirical application: an event study on China, Australia, and the US. The results show that inward capital control measures significantly reduce fund inflows within one month, and restrictive policies tend to have stronger effects than liberalizing ones, with notable heterogeneity across countries. Our work contributes to the growing literature on the use of LLMs in economics by providing both a novel high-frequency policy dataset and a replicable framework for automated classification of capital control events from diverse and evolving information sources.