[2603.21485] Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies

Computer Science > Machine Learning arXiv:2603.21485 (cs) [Submitted on 23 Mar 2026] Title:Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies Authors:Koichi Tanaka, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Yuki Sasamoto, Kei Tateno, Takuma Udagawa, Wei-Wei Du, Yuta Saito View a PDF of the paper titled Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies, by Koichi Tanaka and 8 other authors View PDF HTML (experimental) Abstract:Off-Policy Evaluation (OPE) is an important practical problem in algorithmic ranking systems, where the goal is to estimate the expected performance of a new ranking policy using only offline logged data collected under a different, logging policy. Existing estimators, such as the ranking-wise and position-wise inverse propensity score (IPS) estimators, require the data collection policy to be sufficiently stochastic and suffer from severe bias when the logging policy is fully deterministic. In this paper, we propose novel estimators, Click-based Inverse Propensity Score (CIPS), exploiting the intrinsic stochasticity of user click behavior to address this challenge. Unlike existing methods that rely on the stochasticity of the logging policy, our approach uses click probability as a new form of importance weighting, enabling low-bias OPE even under deterministic logging policies where existing methods incur substantial bias. We provide theoretical analyses of the bias and variance proper...