Training and Evaluating Causal Forecasting Models for Time-Series
Keywords: Time-series forecasting; Causal Inference; Regression Discontinuity Designs; Deep Learning
TL;DR: We design causal time-series forecasting models using orthogonal statistical learning, and evaluate them by creating a test set of treatment effects estimated with Regression Discontinuity Designs.
Abstract: Deep learning time-series models are often used to make forecasts that inform downstream decisions.
Since these decisions can differ from those in the training set, there is an implicit requirement that time-series models will generalize outside of their training distribution.
Despite this core requirement, time-series models are typically trained and evaluated on in-distribution predictive tasks.
We extend the orthogonal statistical learning framework to train causal time-series models that generalize better when forecasting the effect of actions outside of their training distribution.
To evaluate these models, we leverage Regression Discontinuity Designs popular in economics to construct a test set of causal treatment effects.
Primary Area: causal reasoning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 5964
Loading