ExpoCast: Counterfactual Demand and Policy Analytics for the Exhibition Economy via Causal Spatio-Temporal Graphs and LLM-Augmented Policy Embeddings

DOI

10.2991/978-94-6239-774-3_29How to use a DOI?

Keywords

Exhibition Economy; Counterfactual Forecasting; Causal Inference; Graph Neural Networks; Large Language Models

Abstract

Quantitative analysis of the exhibition (MICE) economy lies between black-box forecasters that ignore policy and causal toolkits that ill-handle networked, text-rich data. We propose ExpoCast, delivering counterfactual demand forecasting and subsidy evaluation from one estimator: a heterogeneous spatio-temporal graph over cities, venues, exhibitions and exhibitors; policy embeddings from a frozen LLM; and a doubly-robust orthogonal head whose graph-aware Neyman score yields n 1 / 2 -consistent CATE under graph-induced confounding. On a calibrated MICE simulator and on the Macau tourist-arrivals corpus of Law et al. (2019) as a transfer benchmark, ExpoCast cuts 12-month MAPE by 23-31% over strong baselines and recovers subsidy effects within 0.05 σ , where DML and GRF miss by more than 0.5 σ . A case study identifies second-tier coastal B2B as the locus of the largest marginal returns.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xianzi Li
PY  - 2026
DA  - 2026/09/11
TI  - ExpoCast: Counterfactual Demand and Policy Analytics for the Exhibition Economy via Causal Spatio-Temporal Graphs and LLM-Augmented Policy Embeddings
BT  - Proceedings of the 2026 5th International Conference on Mathematical Statistics and Economic Analysis (MSEA 2026
PB  - Atlantis Press
SP  - 318
EP  - 324
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-774-3_29
DO  - 10.2991/978-94-6239-774-3_29
ID  - Li2026
ER  -