Big Data and Artificial Intelligence as Inputs into Monetary Policymaking at the National Bank of Ukraine

The National Bank of Ukraine (NBU) began using alternative and high-frequency data well before the full-scale invasion, and this capacity became critical after 2022, when the war interrupted official statistics. For monetary policy, this capacity has served two purposes. The first is timeliness: in a fast-changing environment, the Monetary Policy Committee (MPC) needs a reading of prices and economic activity weeks before official data arrive, and the NBU’s nowcasts provide it. The second concerns the assessment of nonstandard shocks to economic activity and inflation, which in wartime have become routine and require a policy response. These assessments draw on millions of online prices, Google Trends, satellite night-light imagery, online job vacancies, fiscal data, and indicators of military activity and infrastructure damage. More recently, the NBU has used large language models to extend the approach to text, including news, social media, and its own communication, and has built a prototype system of AI agents that simulates household survey respondents. Tracing a decade of evolution where each stage introduced new data sources and uncertainties, this paper outlines three key principles for applying AI-generated signals to monetary policy decisions and communication.