What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions

Shuqi Gu, Yongxiang Zhao, Baoyu Jing, Kan Ren
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:37376-37394, 2026.

Abstract

Time series forecasting has become increasingly critical in real-world scenarios, where future sequences are influenced not only by historical patterns but also by forthcoming events. In this context, forecasting must dynamically adapt to complex and stochastic future conditions, which introduces fundamental challenges in both forecasting and evaluation. Traditional methods typically rely on historical data or factual future conditions, while overlooking counterfactual scenarios. Furthermore, many existing approaches are restricted to simple structured conditions, limiting their ability to generalize to the real-world complexities. To address these gaps, we introduce the task of counterfactual time series forecasting with textual conditions, enabling more flexible and condition-aware forecasting. We propose a comprehensive evaluation framework that encompasses both factual and counterfactual settings, even in the absence of ground truth time series. Additionally, we present a novel text-attribution mechanism that distinguishes mutable from immutable factors, thereby improving forecast accuracy under sophisticated and stochastic textual conditions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-gu26r, title = {What if Tomorrow is the World Cup Final? {C}ounterfactual Time Series Forecasting with Textual Conditions}, author = {Gu, Shuqi and Zhao, Yongxiang and Jing, Baoyu and Ren, Kan}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {37376--37394}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/gu26r/gu26r.pdf}, url = {https://proceedings.mlr.press/v306/gu26r.html}, abstract = {Time series forecasting has become increasingly critical in real-world scenarios, where future sequences are influenced not only by historical patterns but also by forthcoming events. In this context, forecasting must dynamically adapt to complex and stochastic future conditions, which introduces fundamental challenges in both forecasting and evaluation. Traditional methods typically rely on historical data or factual future conditions, while overlooking counterfactual scenarios. Furthermore, many existing approaches are restricted to simple structured conditions, limiting their ability to generalize to the real-world complexities. To address these gaps, we introduce the task of counterfactual time series forecasting with textual conditions, enabling more flexible and condition-aware forecasting. We propose a comprehensive evaluation framework that encompasses both factual and counterfactual settings, even in the absence of ground truth time series. Additionally, we present a novel text-attribution mechanism that distinguishes mutable from immutable factors, thereby improving forecast accuracy under sophisticated and stochastic textual conditions.} }
Endnote
%0 Conference Paper %T What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions %A Shuqi Gu %A Yongxiang Zhao %A Baoyu Jing %A Kan Ren %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-gu26r %I PMLR %P 37376--37394 %U https://proceedings.mlr.press/v306/gu26r.html %V 306 %X Time series forecasting has become increasingly critical in real-world scenarios, where future sequences are influenced not only by historical patterns but also by forthcoming events. In this context, forecasting must dynamically adapt to complex and stochastic future conditions, which introduces fundamental challenges in both forecasting and evaluation. Traditional methods typically rely on historical data or factual future conditions, while overlooking counterfactual scenarios. Furthermore, many existing approaches are restricted to simple structured conditions, limiting their ability to generalize to the real-world complexities. To address these gaps, we introduce the task of counterfactual time series forecasting with textual conditions, enabling more flexible and condition-aware forecasting. We propose a comprehensive evaluation framework that encompasses both factual and counterfactual settings, even in the absence of ground truth time series. Additionally, we present a novel text-attribution mechanism that distinguishes mutable from immutable factors, thereby improving forecast accuracy under sophisticated and stochastic textual conditions.
APA
Gu, S., Zhao, Y., Jing, B. & Ren, K.. (2026). What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:37376-37394 Available from https://proceedings.mlr.press/v306/gu26r.html.

Related Material