How Does LLM Help Regional CPI Forecast: An LLM-powered Deep Panel Modeling Framework

2026-04-08

AI Summary

Traditional regional CPI forecasting relies on low-frequency macroeconomic indicators, which struggle to capture timely market fluctuations. This study proposes a novel paradigm that integrates large language models with deep panel data modeling: high-frequency proxy variables are extracted from Weibo text using prompt-based GPT and fine-tuned BERT, then incorporated into a deep panel neural network via a residual joint modeling framework. The approach further introduces a regional homogeneity mechanism and conformal prediction to quantify uncertainty. Empirical results demonstrate that the proposed method significantly improves short-term CPI forecast accuracy and more effectively captures abrupt inflationary shifts, outperforming conventional econometric models.

Abstract

Understanding regional Consumer Price Index (CPI) dynamics is essential for timely and effective economic policymaking. However, traditional modeling procedures typically rely only on parametric panel modeling with low-frequency and high-cost macroeconomic indicators, which often fail to capture rapid market fluctuations and lead to inaccurate predictions. To this end, we propose a residual-joint-modeling framework that integrates large language model (LLM) analyses and social media narratives via a new deep neural network based panel modeling. Specifically, we construct a large narrative corpus from a newly collected {\it Sina Weibo} dataset, and develop a prompt-based GPT model and a series of fine-tuned BERT models to generate high-frequency LLM-induced surrogates for regional CPI. A novel joint modeling strategy is then advocated to transfer the information from these surrogates to the target regional CPI data and hence empower CPI prediction. To solve the joint objectives, we further introduce a new deep panel learning procedure with region-wise homogeneity pursuit, which has its own significance in panel data analysis literature. In addition, conformal-based panel prediction intervals are provided to quantify the uncertainty of the LLM-powered prediction. The proposed approach significantly reduces short-term forecasting errors and more effectively captures abrupt inflationary shifts compared to traditional econometric models. While demonstrated for regional CPI forecasting, the proposed framework is broadly applicable for incorporating insights from LLMs to enhance traditional statistical modeling.

Problem

• regional CPI forecasting
• market fluctuations
• macroeconomic indicators
• prediction accuracy
• panel data modeling

Innovation

• LLM-powered panel modeling
• high-frequency narrative surrogates
• deep panel learning
• conformal prediction intervals
• region-wise homogeneity pursuit