DeepAI AI Chat
Log In Sign Up

Inverse Propensity Score based offline estimator for deterministic ranking lists using position bias

by   Nick Wood, et al.

In this work, we present a novel way of computing IPS using a position-bias model for deterministic logging policies. This technique significantly widens the policies on which OPE can be used. We validate this technique using two different experiments on industry-scale data. The OPE results are clearly strongly correlated with the online results, with some constant bias. The estimator requires the examination model to be a reasonably accurate approximation of real user behaviour.


page 1

page 2

page 3

page 4


When Inverse Propensity Scoring does not Work: Affine Corrections for Unbiased Learning to Rank

Besides position bias, which has been well-studied, trust bias is anothe...

Intervention Harvesting for Context-Dependent Examination-Bias Estimation

Accurate estimates of examination bias are crucial for unbiased learning...

Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model

In real-world recommender systems and search engines, optimizing ranking...

Mitigating the Position Bias of Transformer Models in Passage Re-Ranking

Supervised machine learning models and their evaluation strongly depends...

Ranking metrics on non-shuffled traffic

Ranking metrics are a family of metrics largely used to evaluate recomme...