Two-stage recommender systems first choose a candidate generator and then rank items within the generated set. Because the generator decides which items are available to the ranker, changing the generator changes both the policy value and the data support used to estimate that value. This creates an offline selection problem that standard single-stage objectives do not capture: a policy may look good under a retrieval score or a raw off-policy value estimate, but still be unreliable if it depends on weakly supported generator-item pairs. We propose CASP (Coupled Action-Set Pessimism), a support-aware offline selector for finite libraries of two-stage recommender policies. CASP combines doubly robust value estimation with a support-burden penalty. We show that stagewise rules that ignore downstream continuation value can be arbitrarily suboptimal, and we derive population, finite-class, and reconstructed-propensity guarantees for conservative selection. In simulations and a reconstructed MovieLens 1M application, CASP selects lower-burden policies when estimated value and support credibility are in tension.

Appendix B 4. Ifyouareusingexistingassets (e.g., code, data, models) orcurating/releasingnewassets... (a) Ifyourworkusesexistingassets, didyoucitethecreators?[Yes]See

There is an extensive literature on cost-sensitive classification.

Evaluation plays a crucial role in the development of ranking algorithms on search and recommender systems. It enables online platforms to create user-friendly features that drive commercial success in a steady and effective manner. The online environment is particularly conducive to applying causal inference techniques, such as randomized controlled experiments (known as A/B test), which are often more challenging to implement in fields like medicine and public policy. However, businesses face unique challenges when it comes to effective A/B test. Specifically, achieving sufficient statistical power for conversion-based metrics can be time-consuming, especially for significant purchases like booking accommodations. While offline evaluations are quicker and more cost-effective, they often lack accuracy and are inadequate for selecting candidates for A/B test. To address these challenges, we developed interleaving and counterfactual evaluation methods to facilitate rapid online assessments for identifying the most promising candidates for A/B tests. Our approach not only increased the sensitivity of experiments by a factor of up to 100 (depending on the approach and metrics) compared to traditional A/B testing but also streamlined the experimental process. The practical insights gained from usage in production can also benefit organizations with similar interests.

Off-policy evaluation (OPE) is a critical challenge in robust decision-making that seeks to assess the performance of a new policy using data collected under a different policy. However, the existing OPE methodologies suffer from several limitations arising from statistical uncertainty as well as causal considerations. In this thesis, we address these limitations by presenting three different works. Firstly, we consider the problem of high variance in the importance-sampling-based OPE estimators. We introduce the Marginal Ratio (MR) estimator, a novel OPE method that reduces variance by focusing on the marginal distribution of outcomes rather than direct policy shifts, improving robustness in contextual bandits. Next, we propose Conformal Off-Policy Prediction (COPP), a principled approach for uncertainty quantification in OPE that provides finite-sample predictive intervals, ensuring robust decision-making in risk-sensitive applications. Finally, we address causal unidentifiability in off-policy decision-making by developing novel bounds for sequential decision settings, which remain valid under arbitrary unmeasured confounding. We apply these bounds to assess the reliability of digital twin models, introducing a falsification framework to identify scenarios where model predictions diverge from real-world behaviour. Our contributions provide new insights into robust decision-making under uncertainty and establish principled methods for evaluating policies in both static and dynamic settings.

An increasing number of media streaming services have expanded their offerings to include entities of multiple content types. For instance, audio streaming services that started by offering music only, now also offer podcasts, merchandise items, and videos. Ranking items across different content types into a single slate poses a significant challenge for traditional learning-to-rank (LTR) algorithms due to differing user engagement patterns for different content types. We explore a simple method for cross-content-type ranking, called multinomial blending (MB), which can be used in conjunction with most existing LTR algorithms. We compare MB to existing baselines not only in terms of ranking quality but also from other industry-relevant perspectives such as interpretability, ease-of-use, and stability in dynamic environments with changing user behavior and ranking model retraining. Finally, we report the results of an A/B test from an Amazon Music ranking use-case.

The off-policy paradigm casts recommendation as a counterfactual decision-making task, allowing practitioners to unbiasedly estimate online metrics using offline data. This leads to effective evaluation metrics, as well as learning procedures that directly optimise online success. Nevertheless, the high variance that comes with unbiasedness is typically the crux that complicates practical applications. An important insight is that the difference between policy values can often be estimated with significantly reduced variance, if said policies have positive covariance. This allows us to formulate a pairwise off-policy estimation task: $\Delta\text{-}{\rm OPE}$. $\Delta\text{-}{\rm OPE}$ subsumes the common use-case of estimating improvements of a learnt policy over a production policy, using data collected by a stochastic logging policy. We introduce $\Delta\text{-}{\rm OPE}$ methods based on the widely used Inverse Propensity Scoring estimator and its extensions. Moreover, we characterise a variance-optimal additive control variate that further enhances efficiency. Simulated, offline, and online experiments show that our methods significantly improve performance for both evaluation and learning tasks.

Ad-load balancing is a critical challenge in online advertising systems, particularly in the context of social media platforms, where the goal is to maximize user engagement and revenue while maintaining a satisfactory user experience. This requires the optimization of conflicting objectives, such as user satisfaction and ads revenue. Traditional approaches to ad-load balancing rely on static allocation policies, which fail to adapt to changing user preferences and contextual factors. In this paper, we present an approach that leverages off-policy learning and evaluation from logged bandit feedback. We start by presenting a motivating analysis of the ad-load balancing problem, highlighting the conflicting objectives between user satisfaction and ads revenue. We emphasize the nuances that arise due to user heterogeneity and the dependence on the user's position within a session. Based on this analysis, we define the problem as determining the optimal ad-load for a particular feed fetch. To tackle this problem, we propose an off-policy learning framework that leverages unbiased estimators such as Inverse Propensity Scoring (IPS) and Doubly Robust (DR) to learn and estimate the policy values using offline collected stochastic data. We present insights from online A/B experiments deployed at scale across over 80 million users generating over 200 million sessions, where we find statistically significant improvements in both user satisfaction metrics and ads revenue for the platform.

Off-Policy Estimation (OPE) methods allow us to learn and evaluate decision-making policies from logged data. This makes them an attractive choice for the offline evaluation of recommender systems, and several recent works have reported successful adoption of OPE methods to this end. An important assumption that makes this work is the absence of unobserved confounders: random variables that influence both actions and rewards at data collection time. Because the data collection policy is typically under the practitioner's control, the unconfoundedness assumption is often left implicit, and its violations are rarely dealt with in the existing literature. This work aims to highlight the problems that arise when performing off-policy estimation in the presence of unobserved confounders, specifically focusing on a recommendation use-case. We focus on policy-based estimators, where the logging propensities are learned from logged data. We characterise the statistical bias that arises due to confounding, and show how existing diagnostics are unable to uncover such cases. Because the bias depends directly on the true and unobserved logging propensities, it is non-identifiable. As the unconfoundedness assumption is famously untestable, this becomes especially problematic. This paper emphasises this common, yet often overlooked issue. Through synthetic data, we empirically show how na\"ive propensity estimation under confounding can lead to severely biased metric estimates that are allowed to fly under the radar. We aim to cultivate an awareness among researchers and practitioners of this important problem, and touch upon potential research directions towards mitigating its effects.

They allow us to estimate the performance of a new target recommendation policy based on interaction data logged from a different logging policy (for instance, the current production recommender), thereby reducing the need to run slow and costly A/B tests. Many counterfactual off-policy estimators are based on the inverse propensity scoring (IPS) principle [2, 6, 7, 12]. Given a stochastic logging policy and some mild assumptions, IPS-based estimators are unbiased, but often suffer from high variance. This is true even on industrial-scale data sizes; in particular, if the logging policy is close to being deterministic.