Attribution

• Research & Data Quality
• Article

An Introduction to Robyn’s Open-Source Approach to Media Mix Modeling

• MSI

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.

• Research & Data Quality
• Article

Improve Marketing Mix Model (MMM) Accuracy by Identifying these Effects

• MSI

This study explores the identification of nonlinear and time-varying effects in marketing mix models (MMM). It highlights the challenges of conflation in model selection and proposes a framework for simulating and estimating these effects using Gaussian processes. The study emphasizes the importance of accurately identifying the underlying response to optimize marketing spending.

The research provides insights into the complexities of marketing effectiveness and offers practical solutions for improving model accuracy. By addressing the issue of conflation, the study aims to enhance the decision-making process in marketing strategies.

• Targets & Segments
• Article

Established Activist Brands Have a Competitive Edge

• JOURNAL OF ADVERTISING RESEARCH

Does brand activism—taking a stand on a sociopolitical issue—influence attitudes and purchase intentions, and if so, how? These questions are addressed in new research that identifies a credibility gap between brands that have an established reputation as activists, such as Nike and Ben & Jerry’s, and those that do not. With few exceptions, established activist brands have a lot more to gain than their emergent activist peers when taking a stand.

• Analytics & Data Science
• Article

Data Pooling could Reinvigorate Online Display Ads

• MSI

Buying online display ads in bulk through online exchanges makes it difficult to ascertain the effectiveness of such ads, a situation that’s less than ideal. This is especially true for new websites. One proposed solution is to pool data across advertisers and publishers. Doing so while running matching simulations can substantially improve the welfare of such ads for advertisers, publishers and networks, too.

• Analytics & Data Science
• Article

What are the Drivers Behind Metric Use in a Global Setting?

• MSI

Marketers are under increasing pressure to be accountable for their actions. Using metrics is a big part of how they justify their decisions across the organization. Increasingly, firms are becoming global entities. Yet, there is little to no research looking into what drives metric use across countries. Researchers in this study analyzed over 4,000 marketing mix decisions in 16 countries. Their report offers important insights for top executives who want to understand what is driving downstream managerial metric use.

• Creative & Branded Content
• Article

Brands Should Do More to Protect Their Image Online, Study Shows

• Journal of Advertising Research

Brand safety is a hot topic in programmatic advertising, which is lauded for its efficient distribution but comes with big risks—particularly the unfiltered placement of digital ads next to negative content. New research offers empirical evidence of such risks, including damage to consumers’ perceptions, and calls for brands to do more to protect themselves.

• Audience & Media Measurement
• Article

How Influencer KPI Patterns Differ across Social Media Platforms

• JOURNAL OF ADVERTISING RESEARCH

Brands increasingly use social media influencers as part of their marketing strategy, yet methods for measuring their effectiveness and for choosing optimal partners are unreliable. New research analyzing the key performance indicators (followers and engagement) of 180 influencers, across five social media platforms, identifies patterns that marketers can use toward establishing partnerships with the right influencers.

• Ad Effectiveness & ROI
• Article

How Emissions-Driven Tax Policies Influence Auto Brands’ Advertising Strategies

• JOURNAL OF ADVERTISING RESEARCH

Auto companies in many countries tend to reduce ad spend toward promoting low-emission vehicles in the face of unfavorable tax policies, but this may not be the optimal advertising strategy and can have a profound effect on the rest of the media market, new research has found.

• Audience & Media Measurement
• Article

How Changing Privacy Frameworks Are Affecting Marketing & Measurement

• ARF Research Initiatives

A growing number of privacy regulations and data deprecations are creating a highly complicated landscape for marketers to maneuver through. To help us better understand how these forces affect marketing and marketing effectiveness measurement, the ARF recently gathered a group of experts on privacy-related topics from both practitioner and academic backgrounds, to discuss the key issues and outline ways forward. This report is the result of that effort. It includes an overview of the latest privacy-related macro-trends, implications for marketing and measurement and actionable recommendations.

• Research & Data Quality
• Article

A Guide to Validating Marketing Performance Models

Over the last dozen years, marketers have seen numerous analytical models surface to help guide data driven decision-making. Yet, many remain unsure of how trustworthy such models are. That’s why the Attribution Working Group of the ARF Cross-Platform Measurement Council put together this guidebook to help arm all stakeholders with a basic understanding of marketing performance model validation issues. This paper includes a set of considerations and questions that encourage and facilitate dialog between end clients and model providers about the performance of marketing performance models.