Event Details

Time series predictive inference is an important yet challenging task in economics and business, where existing approaches are often designed for low-frequency, survey-based data. With the recent advances of large language models (LLMs), there is growing potential to leverage high-frequency online text data for improved time series prediction, an area still largely unexplored. This paper proposes the LLM-TS, an LLM-based approach for time series predictive inference incorporating online text data. The LLM-TS is based on a joint time series framework that combines survey-based low-frequency data with LLM-generated high-frequency surrogates. The framework relies only on an error correlation assumption, combining a text-embedding-augmented ARX model for the observed gold-standard measurements with a VARX model for the LLM-generated surrogates. LLM-TS employs LLMs such as ChatGPT and the trained BERT models to construct LLM surrogates. Online text embeddings are extracted via LDA and BERT. We establish the asymptotic properties of the method and provide two forms of constructed prediction intervals. We also extend LLM-TS to incorporate deep learning backbones. To demonstrate the practical power of LLM-TS, we apply it to a critical real-world application: inflation forecast. We construct two large high-frequency online text data sets from the U.S. and China, and use LLMs to extract inflation-related signals from texts that reflect price dynamics. The finite-sample performance and practical advantages of LLM-TS are illustrated through extensive simulations and two noisy real data examples, highlighting its potential to improve time series prediction in economic applications. This is a joint work with Yingying Fan, Ao Sun and Yurou Wang.

Zoom connection
Meeting ID: 927 5174 4356
Passcode: 2025

Host: DJ Ashok
POC: Maura Covaci

Speaker Bio

Jinchi Lv (http://faculty.marshall.usc.edu/jinchi-lv/) is Kenneth King Stonier Chair in Business Administration, Department Chair, Professor in Data Sciences and Operations Department of the Marshall School of Business at the University of Southern California, and Professor in Department of Mathematics at USC. He received his Ph.D. in Mathematics from Princeton University in 2007. He was McAlister Associate Professor in Business Administration at USC from 2016-2019. His research interests include statistics, data science, artificial intelligence, machine learning, and business applications as well as blockchain and large language models. His papers have been published in journals in statistics, economics, business, computer science, information theory, neuroscience, and biology.