# Taking the Counterfactual Online: Efficient and Unbiased Online Evaluation for Ranking

arXiv: https://arxiv.org/abs/2007.12719 · HTML: https://mlsanity.com/paper/2007.12719/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning](https://mlsanity.com/paper/2111.14552/) (2021)
- [Safe Exploration for Efficient Policy Evaluation and Comparison](https://mlsanity.com/paper/2202.13234/) (2022)
- [Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization](https://mlsanity.com/paper/2305.01522/) (2023)
- [SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits](https://mlsanity.com/paper/2301.12357/) (2023)
- [Recent Advances in the Foundations and Applications of Unbiased Learning to Rank](https://mlsanity.com/paper/2305.02914/) (2023)
- [Theoretical Analysis on the Efficiency of Interleaved Comparisons](https://mlsanity.com/paper/2306.10023/) (2023)
- [Accelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap](https://mlsanity.com/paper/2607.14604/) (2026)
- [Exposure-Based Reinforcement Learning to Rank](https://mlsanity.com/paper/2607.18689/) (2026)

## Abstract (arXiv)

Counterfactual evaluation can estimate Click-Through-Rate (CTR) differences between ranking systems based on historical interaction data, while mitigating the effect of position bias and item-selection bias. We introduce the novel Logging-Policy Optimization Algorithm (LogOpt), which optimizes the policy for logging data so that the counterfactual estimate has minimal variance. As minimizing variance leads to faster convergence, LogOpt increases the data-efficiency of counterfactual estimation. LogOpt turns the counterfactual approach - which is indifferent to the logging policy - into an online approach, where the algorithm decides what rankings to display. We prove that, as an online evaluation method, LogOpt is unbiased w.r.t. position and item-selection bias, unlike existing interleaving methods. Furthermore, we perform large-scale experiments by simulating comparisons between thousands of rankers. Our results show that while interleaving methods make systematic errors, LogOpt is as efficient as interleaving without being biased.