Ad-load balancing is a critical challenge in online advertising systems,...
Off-Policy Estimation (OPE) methods allow us to learn and evaluate
decis...
Approaches to recommendation are typically evaluated in one of two ways:...
Modern web-based platforms show ranked lists of recommendations to users...
In this paper we propose RecFusion, which comprise a set of diffusion mo...
Online experiments such as Randomised Controlled Trials (RCTs) or A/B-te...
The bandit paradigm provides a unified modeling framework for problems t...
The ability to answer causal questions is crucial in many domains, as ca...
Both in academic and industry-based research, online evaluation methods ...
In machine learning we often try to optimise a decision rule that would ...
In academic literature, recommender systems are often evaluated on the t...