Cross-Platform

• Audience & Media Measurement
• Article

Why Don’t Advertisers Experiment More? The Economics Behind Incrementality Testing

• ARF; MSI

Randomized experiments are widely viewed as the gold standard for measuring advertising incrementality, yet advertisers run them far less often than theory would predict. This MSI working paper develops a game-theoretic model of online advertising to explain why. By explicitly modeling the fixed and opportunity costs of experimentation—and the strategic role of ad platforms in setting reserve prices—the study shows how platforms may rationally discourage experimentation even when learning ad effectiveness could improve allocation efficiency. The findings offer a new economic explanation for persistently low experimentation rates in digital advertising markets.

• Audience & Media Measurement
• Article

Predicting What Moves the Needle: Marketing Mix Modeling After Cookies

• ARF; MSI

As privacy regulations and the deprecation of third-party cookies limit access to individual-level consumer data, advertisers are increasingly forced to rely on aggregate metrics to evaluate marketing effectiveness. This MSI working paper introduces a novel, two-stage, marketing mix modeling framework designed specifically for cookie-free environments. By combining machine-learning–based directional prediction with classical econometric calibration, the approach demonstrates how firms can extract reliable signals about campaign effectiveness—even from short, noisy, aggregate time series—while maintaining interpretability and practical relevance for marketing decision-making.

• Targets & Segments
• Article

Why Irregular Ad Scheduling Wins: Uncovering the Hidden Dynamics of Skippable Ad Acceptance

• ARF
• JOURNAL OF ADVERTISING RESEARCH

A large-scale analysis of clickstream data reveals that how often and how regularly pre-roll skippable ads are shown significantly influences whether users accept or skip them. Using advanced modeling, researchers find that less frequent and more irregular exposure increases the hidden “acceptance propensity” underlying viewing behavior. These findings challenge conventional scheduling tactics and offer new strategies for maximizing skippable ad effectiveness.

• Research & Data Quality
• Article

Navigating Identity Loss: Measurement and Targeting in a Privacy-First Era

• ARF
• ARF Analytics Council

How is the loss of digital identifiers reshaping advertising research? This guide, by the ARF Analytics Council, offers advertising researchers a deep dive into the privacy-first landscape, covering regulatory impacts, measurement challenges and practical identity solutions—from synthetic IDs to advanced modeling—to enable successful targeting and attribution in a fragmented ecosystem.

• Audience & Media Measurement
• Article

Discover the Current State of Attention Metrics in Today’s Marketplace

• ARF
• ARF

The ARF Attention Report explores the evolving role of attention metrics in advertising, examining their adoption, effectiveness and challenges across agencies and brand-side advertisers. The data is based on a survey measuring the array of metrics currently used by advertisers and agencies across various platforms and industries. As the advertising industry increasingly values consumer engagement beyond traditional reach-based metrics, attention metrics have gained prominence, though adoption and integration remain uneven. Key findings include that attention metrics are gaining traction, with 64% of agencies and 43% of advertisers reporting frequent or constant use. Engagement rates (58%) and time spent (55%) are the most widely used attention metrics due to their accessibility, while advanced methods like biometric response (16%) and neuro measures (13%) remain relatively niche.

• Future States & AI
• Article

Dive Deep into Retail Media Networks: One of the Fastest Growing Channels in the US

• ARF
• ARF

Retail Media Networks (RMNs) have emerged as one of the fastest-growing advertising channels in the U.S., transforming how brands reach and engage consumers. Leveraging first-party data, RMNs enable targeted, measurable campaigns across retailers’ ecosystems, opening a unique blend of performance-driven and brand-building opportunities. Learn about this emerging channel, including the commonalities and differences in how they are being used between advertisers and agencies, in this deep dive into RMNs.

• Future States & AI
• Article

Tracking the Why Over Time: A New Era of AI-Powered Advertising Research

• ARF
• Journal of Advertising Research

A new framework for measuring advertising impact over time—“intensive longitudinal mediation”—uses AI and big data to reveal when and why ads work. This approach helps marketers capture psychological shifts in real-time, going beyond static analysis to uncover how advertising drives behavior over days or weeks.

• Targets & Segments
• Article

Learn How to Train LLMs to Identify Implicit Consumer Needs

This study explores the potential of large language models (LLMs) to revolutionize marketing research. By partnering with a Fortune 500 food company, the authors replicated qualitative and quantitative studies using GPT-4. The findings indicate that LLMs can effectively generate synthetic respondents, moderate in-depth interviews and perform data analysis tasks, matching or even surpassing human performance in certain aspects. The study highlights the benefits of a Human-LLM hybrid approach, where LLMs assist in various stages of the research process, from study design to data analysis. This approach not only enhances efficiency but also uncovers new insights that might be overlooked by human researchers alone.

• Audience & Media Measurement
• Article

Evaluate Identity Resolution Effectively with this Council Guide

• ARF ORIGINAL RESEARCH

Identity resolution (IDR) is crucial in media measurement and advertising, connecting media messaging to individuals. This guide, produced by the ARF Identity Resolution Working Group (of the ARF Cross-Platform Measurement Council), explores different units of analysis in IDR beyond individuals, such as households, geography and cohorts and their implications for matching quality, targeting and marketing success.  

• Research & Data Quality
• Article

LOLA: Revolutionizing Content Experiments with LLM-Assisted Online Learning

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.