no code implementations • 9 May 2024 • Shashank Gupta, Olivier Jeunen, Harrie Oosterhuis, Maarten de Rijke
The foundation of our framework is the derivation of an equivalent baseline correction for all of the existing control variates.
no code implementations • 3 May 2024 • Olivier Jeunen, Jatin Mandav, Ivan Potapov, Nakul Agarwal, Sourabh Vaid, Wenzhe Shi, Aleksei Ustimenko
We frame this as a decision-making task, where the scalarisation weights are actions taken to maximise an overall North Star reward (e. g. long-term user retention or growth).
no code implementations • 6 Feb 2024 • Olivier Jeunen, Aleksei Ustimenko
Online controlled experiments are a crucial tool to allow for confident decision-making in technology companies.
no code implementations • 8 Jan 2024 • Shubham Baweja, Neeti Pokharna, Aleksei Ustimenko, Olivier Jeunen
The main culprit for this inefficiency is the variance of the online metrics.
no code implementations • 8 Jan 2024 • Hitesh Sagtani, Olivier Jeunen, Aleksei Ustimenko
Many platforms on the web present ranked lists of content to users, typically optimized for engagement-, satisfaction- or retention- driven metrics.
no code implementations • 4 Dec 2023 • Olivier Jeunen, Hitesh Sagtani, Himanshu Doi, Rasul Karimov, Neeti Pokharna, Danish Kalim, Aleksei Ustimenko, Christopher Green, Wenzhe Shi, Rishabh Mehrotra
We highlight (1) neural networks' ability to handle large training data size, user- and item-embeddings allows for more accurate models than GBDTs in this setting, and (2) because GBDTs are less reliant on specialised hardware, they can provide an equally accurate model at a lower cost.
no code implementations • 19 Sep 2023 • Hitesh Sagtani, Madan Jhawar, Rishabh Mehrotra, Olivier Jeunen
We start by presenting a motivating analysis of the ad-load balancing problem, highlighting the conflicting objectives between user satisfaction and ads revenue.
1 code implementation • 8 Sep 2023 • Olivier Jeunen, Ben London
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.
1 code implementation • 27 Jul 2023 • Olivier Jeunen, Ivan Potapov, Aleksei Ustimenko
Through a correlation analysis between off- and on-line experiments conducted on a large-scale recommendation platform, we show that our unbiased DCG estimates strongly correlate with online reward, even when some of the metric's inherent assumptions are violated.
1 code implementation • 26 Jul 2023 • Olivier Jeunen
Empirical insights from a large-scale social media platform show how our probabilistic position bias model more accurately captures empirical exposure than existing models, and paves the way for unbiased evaluation and learning-to-rank.
1 code implementation • 15 Jun 2023 • Gabriel Bénédict, Olivier Jeunen, Samuele Papa, Samarth Bhargav, Daan Odijk, Maarten de Rijke
In this paper we propose RecFusion, which comprise a set of diffusion models for recommendation.
1 code implementation • 21 Apr 2023 • Olivier Jeunen
Online experiments such as Randomised Controlled Trials (RCTs) or A/B-tests are the bread and butter of modern platforms on the web.
no code implementations • 2 Feb 2023 • Bram van den Akker, Olivier Jeunen, Ying Li, Ben London, Zahra Nazari, Devesh Parekh
The research literature on these topics is broad and vast, but this can overwhelm practitioners, whose primary aim is to solve practical problems, and therefore need to decide on a specific instantiation or approach for each project.
1 code implementation • 11 Oct 2022 • Olivier Jeunen, Ciarán M. Gilligan-Lee, Rishabh Mehrotra, Mounia Lalmas
We address this challenge by aiming to learn the effect of a single-intervention from both observational data and sets of interventions.
no code implementations • 18 Sep 2022 • Imad Aouali, Amine Benhalloum, Martin Bompaire, Benjamin Heymann, Olivier Jeunen, David Rohde, Otmane Sakhi, Flavian vasile
Naturally, the reason for this is that we can directly measure utility metrics that rely on interventions, being the recommendations that are being shown to users.
no code implementations • 18 Sep 2019 • Olivier Jeunen, Dmytro Mykhaylov, David Rohde, Flavian vasile, Alexandre Gilotte, Martin Bompaire
In order to handle this "bandit-feedback" setting, several Counterfactual Risk Minimisation (CRM) methods have been proposed in recent years, that attempt to estimate the performance of different policies on historical data.
no code implementations • 26 Jul 2019 • Olivier Jeunen, David Rohde, Flavian vasile
The procedure aims to give an answer to the question: "Given the natural sequence of user-item interactions up to time t, can we predict which item the user will interact with at time t+1?".
no code implementations • 24 Apr 2019 • Dmytro Mykhaylov, David Rohde, Flavian vasile, Martin Bompaire, Olivier Jeunen
There are three quite distinct ways to train a machine learning model on recommender system logs.