An AI-powered Tool for Central Bank Business Liaisons: Quantitative Indicators and On-demand Insights from Firms

2025-06-23

AI Summary

Amid rising policy uncertainty, central banks increasingly rely on enterprise liaison programs for soft information; however, analyzing 25 years of unstructured textual data poses challenges in efficient retrieval, joint topic–sentiment–uncertainty analysis, and precise extraction of numerical information (e.g., wages, prices). Method: This paper pioneers the systematic application of modern NLP techniques to central bank enterprise liaison texts, developing an AI-driven text analytics and retrieval platform that integrates classical methods with large language models, and proposes a machine learning–based nowcasting framework for quantifying high-dimensional sparse text features. Contribution/Results: The resulting soft indicators significantly improve short-term wage growth forecasting accuracy, uncovering sparse yet highly predictive signals. Empirical results robustly confirm the incremental value of soft information for macroeconomic forecasting.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Calibration & Uncertainty Quantification
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In a world of increasing policy uncertainty, central banks are relying more on soft information sources to complement traditional economic statistics and model-based forecasts. One valuable source of soft information comes from intelligence gathered through central bank liaison programs -- structured programs in which central bank staff regularly talk with firms to gather insights. This paper introduces a new text analytics and retrieval tool that efficiently processes, organises, and analyses liaison intelligence gathered from firms using modern natural language processing techniques. The textual dataset spans 25 years, integrates new information as soon as it becomes available, and covers a wide range of business sizes and industries. The tool uses both traditional text analysis techniques and powerful language models to provide analysts and researchers with three key capabilities: (1) quickly querying the entire history of business liaison meeting notes; (2) zooming in on particular topics to examine their frequency (topic exposure) and analysing the associated tone and uncertainty of the discussion; and (3) extracting precise numerical values from the text, such as firms' reported figures for wages and prices growth. We demonstrate how these capabilities are useful for assessing economic conditions by generating text-based indicators of wages growth and incorporating them into a nowcasting model. We find that adding these text-based features to current best-in-class predictive models, combined with the use of machine learning methods designed to handle many predictors, significantly improves the performance of nowcasts for wages growth. Predictive gains are driven by a small number of features, indicating a sparse signal in contrast to other predictive problems in macroeconomics, where the signal is typically dense.

Problem

• Processes and analyzes central bank liaison intelligence using NLP
• Provides querying and topic analysis of business meeting notes
• Improves wage growth nowcasting with text-based indicators

Innovation

• AI-powered text analytics for central bank intelligence
• Natural language processing for real-time data integration
• Machine learning enhances nowcasting model performance