TL;DR
This paper introduces counterfactual time series forecasting with textual conditions, proposing a new task, evaluation framework, and a text-attribution mechanism to handle complex, stochastic future scenarios.
Contribution
It defines a novel forecasting task incorporating textual conditions, develops an evaluation framework for factual and counterfactual scenarios, and introduces a text-attribution method for improved accuracy.
Findings
The proposed framework effectively evaluates both factual and counterfactual forecasts.
The text-attribution mechanism improves forecast accuracy under complex textual conditions.
The approach generalizes to real-world scenarios with stochastic and complex future events.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
