Continuous and efficient experimentation is key to the practical success of user-facing applications on the web, both through online A/B-tests and off-policy evaluation. Despite their shared objective---estimating the incremental value of a treatment---these domains often operate in isolation, utilising distinct terminologies and statistical toolkits. This paper bridges that divide by establishing a formal equivalence between their canonical variance reduction methods. We prove that the standard online Difference-in-Means estimator is mathematically identical to an off-policy Inverse Propensity Scoring estimator equipped with an optimal (variance-minimising) additive control variate. Extending this unification, we demonstrate that widespread regression adjustment methods (such as CUPED, CUPAC, and ML-RATE) are structurally equivalent to Doubly Robust estimation. This unified view extends our understanding of commonly used approaches, and can guide practitioners and researchers working on either class of problems.

Online evaluation of ranking and retrieval systems often relies on downstream monetization metrics such as app revenue or creator earnings. These metrics are typically heavy-tailed, with a small fraction of users dominating both mean and variance, leading to low statistical power and unreliable conclusions in A/B experiments -- especially under limited traffic. We present a practical framework for variance reduction in online experiments by combining post-stratification with CUPED. Our approach leverages pre-experiment covariates to improve the sensitivity of monetization experiments without requiring additional traffic. Deployed at ShareChat across ranking-driven monetization experiments, the method substantially reduces variance and improves decision stability, achieving equivalent statistical confidence with ~45\% less traffic than standard metrics. We further discuss practical design choices, guardrails, and limitations, providing guidance on when post-stratification is appropriate for real-world information retrieval and Recommendation systems.

Off-policy estimation (OPE) methods enable unbiased offline evaluation of recommender systems, directly estimating the online reward some target policy would have obtained, from offline data and with statistical guarantees. The theoretical elegance of the framework combined with practical successes have led to a surge of interest, with many competing estimators now available to practitioners and researchers. Among these, Doubly Robust methods provide a prominent strategy to combine value- and policy-based estimators. In this work, we take an alternative perspective to combine a set of OPE estimators and their associated confidence intervals into a single, more accurate estimate. Our approach leverages a correlated fixed-effects meta-analysis framework, explicitly accounting for dependencies among estimators that arise due to shared data. This yields a best linear unbiased estimate (BLUE) of the target policy's value, along with an appropriately conservative confidence interval that reflects inter-estimator correlation. We validate our method on both simulated and real-world data, demonstrating improved statistical efficiency over existing individual estimators.

Recommender systems are inherently decision-making systems, taking actions that have consequences for the world around them.Some consequences might be desirable (for example, growing the user base for an online platform), others might be unintended (for example, amplifying inequality among item providers).In order to reason about these consequences, we need to resort to methods from the literature on causal inference.Whilst this research area has seen a growing interest in recent years, there is an abundance of open research questions from how we should model large-scale recommender systems in such causal frameworks, to what the limitations are for causal identifiability in general settings, and how we can properly handle confounding variables.The CONSEQUENCES workshop series aims to bring together researchers and practitioners who are interested in this research topic, and wish to help shape its future.

Approaches to recommendation are typically evaluated in one of two ways: (1) via a (simulated) online experiment, often seen as the gold standard, or (2) via some offline evaluation procedure, where the goal is to approximate the outcome of an online experiment. Several offline evaluation metrics have been adopted in the literature, inspired by ranking metrics prevalent in the field of Information Retrieval. (Normalised) Discounted Cumulative Gain (nDCG) is one such metric that has seen widespread adoption in empirical studies, and higher (n)DCG values have been used to present new methods as the state-of-the-art in top-n recommendation for many years.

Online controlled experiments are a crucial tool to allow for confident decision-making in technology companies. A North Star metric is defined (such as long-term revenue or user retention), and system variants that statistically significantly improve on this metric in an A/B-test can be considered superior. North Star metrics are typically delayed and insensitive. As a result, the cost of experimentation is high: experiments need to run for a long time, and even then, type-II errors (i.e. false negatives) are prevalent.

The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. With unbiasedness comes potentially high variance, and prevalent methods exist to reduce estimation variance. These methods typically make use of control variates, either additive (i.e., baseline corrections or doubly robust methods) or multiplicative (i.e., self-normalisation).

Online controlled experiments, colloquially known as A/B-tests, are the bread and butter of real-world recommender system evaluation. Typically, end-users are randomly assigned some system variant, and a plethora of metrics are then tracked, collected, and aggregated throughout the experiment. A North Star metric (e.g. long-term growth or revenue) is used to assess which system variant should be deemed superior. As a result, most collected metrics are supporting in nature, and serve to either (i) provide an understanding of how the experiment impacts user experience, or (ii) allow for confident decision-making when the North Star metric moves insignificantly (i.e. a false negative or type-II error). The latter is not straightforward: suppose a treatment variant leads to fewer but longer sessions, with more views but fewer engagements; should this be considered a positive or negative outcome?

Real-world recommender systems often need to balance multiple objectives when deciding which recommendations to present to users. These include behavioural signals (e.g. clicks, shares, dwell time), as well as broader objectives (e.g. diversity, fairness). Scalarisation methods are commonly used to handle this balancing task, where a weighted average of per-objective reward signals determines the final score used for ranking. Naturally, how these weights are computed exactly, is key to success for any online platform.

Recommender systems are inherently decision-making systems, taking actions that have consequences for the world around them. Some consequences might be desirable (for example, growing the user base for an online platform), others might be unintended (for example, amplifying inequality among item providers). In order to reason about these consequences, we need to resort to methods from the literature on causal inference. Whilst this research area has seen a growing interest in recent years, there is an abundance of open research questions from how we should model large-scale recommender systems in such causal frameworks, to what the limitations are for causal identifiability in general settings, and how we can properly handle confounding variables. The CONSEQUENCES workshop series aims to bring together researchers and practitioners who are interested in this research topic, and wish to help shape its future.

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: Δ-OPE.

Emerging short-video platforms like TikTok, Instagram Reels, and ShareChat present unique challenges for recommender systems, primarily originating from a continuous stream of new content. ShareChat alone receives approximately 2 million pieces of fresh content daily, complicating efforts to assess quality, learn effective latent representations, and accurately match content with the appropriate user base, especially given limited user feedback. Embedding-based approaches are a popular choice for industrial recommender systems because they can learn low-dimensional representations of items, leading to effective recommendation that can easily scale to millions of items and users.

The bandit paradigm provides a unified modeling framework for problems that require decision-making under uncertainty. Because many business metrics can be viewed as rewards (a.k.a. utilities) that result from actions, bandit algorithms have seen a large and growing interest from industrial applications, such as search, recommendation and advertising. Indeed, with the bandit lens comes the promise of direct optimisation for the metrics we care about.

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.

Online advertising opportunities are sold through auctions, billions of times every day across the web. Advertisers who participate in those auctions need to decide on a bidding strategy: how much they are willing to bid for a given impression opportunity. Deciding on such a strategy is not a straightforward task, because of the interactive and reactive nature of the repeated auction mechanism. Indeed, an advertiser does not observe counterfactual outcomes of bid amounts that were not submitted, and successful advertisers will adapt their own strategies based on bids placed by competitors. These characteristics complicate effective learning and evaluation of bidding strategies based on logged data alone.

Modern web-based platforms often show ranked lists of recommendations to users, in an attempt to maximise user satisfaction or business metrics. Typically, the goal of such systems boils down to maximising the exposure probability —conversely, minimising the rank— for items that are deemed “reward-maximising” according to some metric of interest. This general framing comprises music or movie streaming applications, as well as e-commerce, restaurant or job recommendations, and even web search. Position bias or user models can be used to estimate exposure probabilities for each use-case, specifically tailored to how users interact with the presented rankings. A unifying factor in these diverse problem settings is that typically only one or several items will be engaged with (clicked, streamed, purchased, et cetera) before a user leaves the ranked list.

Recommender systems make algorithmic decisions about what will be shown to whom, billions of times every day across the web. These decisions have consequences that can often be far-reaching. Indeed, users that are exposed to certain items, might be convinced to explore interests that are novel to them. At the same time, exposure is often linked to economic incentives for the item producer, which platform-level metrics will be impacted by as well. Feedback loops in existing systems also imply that algorithmic decisions made by the model itself, have an impact on the data future model iterations will be trained and evaluated on.

Modern recommender systems are often modelled under the sequential decision-making paradigm, where the systemdecideswhich recommendations to show in order to maximise some notion of either imminent or long-term reward. Such methods often require an explicit model of the reward a certain context-action pair will yield – for example, the probability of a click on a recommendation. This common machine learning task is highly non-trivial, as the data-generating process for contexts and actions can be skewed by the recommender system itself. Indeed, when the deployed recommendation policy at data collection time does not pick its actions uniformly-at-random, this leads to a selection bias that can impede effective reward modelling. This in turn makes off-policy learning – the typical setup in industry – particularly challenging. Existing approaches for value-based learning break down in such environments. In this work, we propose and validate a generalpessimisticreward modelling approach for off-policy learning in recommendation. Bayesian uncertainty estimates allow us to express scepticism about our own reward model, which can in turn be used to generate a conservative decision rule. We show how it alleviates a well-known decision making phenomenon known as the Optimiser’s Curse, and draw parallels with existing work on pessimistic policy learning. Leveraging the available closed-form expressions for both the posterior mean and variance when a ridge regressor models the reward, we show how to apply pessimism effectively and efficiently to an off-policy recommendation use-case. Empirical observations in a wide range of simulated environments show that pessimistic decision-making leads to a significant and robust increase in recommendation performance. The merits of our approach are most outspoken in realistic settings with limited logging randomisation, limited training samples, and larger action spaces. We discuss the impact of our contributions in the context of related applications like computational advertising, and present a scope for future research based on hybrid off-/on-policy bandit learning methods for recommendation.

Recommender systems are more and more often modelled as repeated decision making processes – deciding which (ranking of) items to recommend to a given user. Each decision to recommend or rank an item has a significant impact on immediate and future user responses, long-term satisfaction or engagement with the system, and possibly valuable exposure for the item provider. This interactive and interventionist view of the recommender uncovers a plethora of unanswered research questions, as it complicates the typically adopted offline evaluation or learning procedures in the field. We need an understanding of causal inference to reason about (possibly unintended) consequences of the recommender, and a notion of counterfactuals to answer common “what if”-type questions in learning and evaluation. Advances at the intersection of these fields can foster progress in effective, efficient and fair learning and evaluation from logged data. These topics have been emerging in the Recommender Systems community for a while, but we firmly believe in the value of a dedicated forum and place to learn and exchange ideas. We welcome contributions from both academia and industry and bring together a growing community of researchers and practitioners interested in sequential decision making, offline evaluation, batch policy learning, fairness in online platforms, as well as other related tasks, such as A/B testing.

Methods for bandit learning from user interactions often require a model of the reward a certain context-action pair will yield – for example, the probability of a click on a recommendation. This common machine learning task is highly non-trivial, as the data-generating process for contexts and actions is often skewed by the recommender system itself. Indeed, when the deployed recommendation policy at data collection time does not pick its actions uniformly-at-random, this leads to a selection bias that can impede effective reward modelling. This in turn makes off-policy learning – the typical setup in industry – particularly challenging.

The contextual bandit paradigm provides a general framework for decision-making under uncertainty. It is theoretically well-defined and well-studied, and many personalisation use-cases can be cast as a bandit learning problem. Because this allows for the direct optimisation of utility metrics that rely on online interventions (such as click-through-rate (CTR)), this framework has become an attractive choice to practitioners. Historically, the literature on this topic has focused on a one-sided, user-focused notion of utility, overall disregarding the perspective of content providers in online marketplaces (for example, musical artists on streaming services). If not properly taken into account – recommendation systems in such environments are known to lead to unfair distributions of attention and exposure, which can directly affect the income of the providers. Recent work has shed a light on this, and there is now a growing consensus that some notion of “equity of exposure” might be preferable to implement in many recommendation use-cases.

Conventional approaches to recommendation often do not explicitly take into account information on previously shown recommendations and their recorded responses. One reason is that, since we do not know the outcome of actions the system did not take, learning directly from such logs is not a straightforward task. Several methods for off-policy or counterfactual learning have been proposed in recent years, but their efficacy for the recommendation task remains understudied. Due to the limitations of offline datasets and the lack of access of most academic researchers to online experiments, this is a non-trivial task. Simulation environments can provide a reproducible solution to this problem.

Recent work has shown that, despite their simplicity, item-based models optimised through ridge regression can attain highly competitive results on collaborative filtering tasks. As these models are analytically computable and thus forgo the need for often expensive iterative optimisation procedures, they are an attractive choice for practitioners. We study the applicability of such closed-form models to implicit-feedback collaborative filtering when additional side-information or metadata about items is available. Two complementary extensions to the easer paradigm are proposed, based on collective and additive models. Through an extensive empirical analysis on several large-scale datasets, we show that our methods can effectively exploit side-information whilst retaining a closed-form solution, and improve upon the state-of-the-art without increasing the computational complexity of the original easer approach. Additionally, empirical results demonstrate that the use of side-information leads to more “long tail” items being recommended, benefiting the recommendations’ coverage of the item catalogue.

Recommender systems are typically evaluated in an offline setting. A subset of the available user-item interactions is sampled to serve as test set, and some model trained on the remaining data points is then evaluated on its performance to predict which interactions were left out. Alternatively, in an online evaluation setting, multiple versions of the system are deployed and various metrics for those systems are recorded. Systems that score better on these metrics, are then typically preferred. Online evaluation is effective, but inefficient for a number of reasons. Offline evaluation is much more efficient, but current methodologies often fail to accurately predict online performance. In this work, we identify three ways to improve and extend current work on offline evaluation methodologies. More specifically, we believe there is much room for improvement in temporal evaluation, off-policy evaluation, and moving beyond using just clicks to evaluate performance.

The problem of computing all pairwise similarities in a large collection of vectors is a well-known and common data mining task. As the number and dimensionality of these vectors keeps increasing, however, currently existing approaches are often unable to meet the strict efficiency requirements imposed by the environments they need to perform in. Real-time neighbourhood-based collaborative filtering (CF) is one example of such an environment in which performance is critical.

Recommender systems are typically evaluated using either offline methods, online methods, or through user studies. In this paper we take an episode mining approach to analysing recommender system data and we demonstrate how we can use SNIPER, a tool for interactive pattern mining, to analyse and understand the behaviour of recommender systems. We describe the required data format, and present a useful scenario of how a user can interact with the system to answer questions about the quality of recommendations.