# Causal Transfer Random Forest: Combining Logged Data and Randomized Experiments for Robust Prediction

arXiv: https://arxiv.org/abs/2010.08710 · HTML: https://mlsanity.com/paper/2010.08710/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Beyond Discriminant Patterns: On the Robustness of Decision Rule Ensembles](https://mlsanity.com/paper/2109.10432/) (2021)
- [Synthesized Difference in Differences](https://mlsanity.com/paper/2105.00455/) (2021)
- [Mitigating Frequency Bias in Next-Basket Recommendation via Deconfounders](https://mlsanity.com/paper/2211.09072/) (2022)
- [Counterfactual Evaluation of Ads Ranking Models through Domain Adaptation](https://mlsanity.com/paper/2409.19824/) (2024)
- [Learning Deployable Causal Action Geometry under Temporal Non-Stationarity](https://mlsanity.com/paper/2610.16644/) (2026)

## Abstract (arXiv)

It is often critical for prediction models to be robust to distributional shifts between training and testing data. From a causal perspective, the challenge is to distinguish the stable causal relationships from the unstable spurious correlations across shifts. We describe a causal transfer random forest (CTRF) that combines existing training data with a small amount of data from a randomized experiment to train a model which is robust to the feature shifts and therefore transfers to a new targeting distribution. Theoretically, we justify the robustness of the approach against feature shifts with the knowledge from causal learning. Empirically, we evaluate the CTRF using both synthetic data experiments and real-world experiments in the Bing Ads platform, including a click prediction task and in the context of an end-to-end counterfactual optimization system. The proposed CTRF produces robust predictions and outperforms most baseline methods compared in the presence of feature shifts.