In the rapidly evolving digital content landscape, media firms and news publishers require automated and efficient methods to enhance user engagement. This study introduces the LLM-Assisted Online Learning Algorithm (LOLA), a novel framework that integrates Large Language Models (LLMs) with adaptive experimentation to optimize content delivery. Leveraging a large-scale dataset from Upworthy, which includes 17,681 headline A/B tests, the study investigates three pure-LLM approaches and finds that prompt-based methods perform poorly, while embedding-based classification models and fine-tuned open-source LLMs achieve higher accuracy.
LOLA combines the best pure-LLM approach with the Upper Confidence Bound (UCB) algorithm to allocate traffic and maximize clicks adaptively. Numerical experiments on data from the website Upworthy show that LOLA outperforms the standard A/B test method, pure bandit algorithms and pure-LLM approaches, particularly in scenarios with limited experimental traffic. This scalable approach is applicable to content experiments across various settings where firms seek to optimize user engagement, including digital advertising and social media recommendations.
Member Only Access
On October 30th, the ARF’s Organizational Council presented the results of the 2024 Organizational Benchmark Survey. This 3rd wave of the Benchmark Survey followed the 1st and the 2nd waves, which took place in 2019 and 2021, respectively. Council Chair Susan Pizzaro’s presentation touched on trends in research department structures, budgets and resources; changes in valued skills and tools used; and satisfaction with the value brought by insights and analytics teams. Afterward, Becky Bach of Pernod Ricard USA and Jim Spaeth of Sequent Partners joined Susan in a discussion moderated by ARF’s Chief Research Officer Paul Donato.
Member Only Access
As privacy-centric changes reshape the digital advertising landscape, deterministic attribution and measurement of advertising-related user behavior are increasingly constrained. In response, there has been a resurgence in the use of traditional probabilistic measurement techniques, such as media and marketing mix modeling (m/MMM), particularly among digital-first advertisers. To address the gap for small and midsize businesses, marketing data scientists at Meta have developed the open-source computational package Robyn, designed to facilitate the adoption of m/MMM for digital advertising measurement.
Robyn is a widely adopted and actively maintained open-source tool that continually evolves. This article explores the computational components and design choices that underpin Robyn, emphasizing how it “packages up” m/MMM to promote organizational acceptance and mitigate common biases. The solutions described are not definitive but outline the pathways that the Robyn community has embarked on.
Member Only Access
Attendees joined us on October 23 for our annual OTT conference, offering the latest research on shifts in the TV and video landscape, viewer behavior, and cross-platform measurement. Industry experts discussed trends in viewing habits, advertising innovations, and predictions for 2025. Attendees also had the opportunity to participate in discussions and network with industry peers over breakfast, lunch, and the cocktail reception.
Member Only Access
