Analytics & Data Science

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.

Member Only Access

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.

Member Only Access

Principles of Data Quality

  • Gerard Broussard
  • The Coalition of Innovative Media Measurement

To improve data quality, the marketing and advertising industry could establish a “Principles of Data Quality” disclosure; create a roster of items to ask of data suppliers; request transparency—data firm disclosures—including consumer authentication procedures, multiple data source descriptions, model target techniques and testing results, recency of data, integration techniques, data labeling, and top-line descriptions for all of the above; create best practice standards.

Member Only Access

Measuring the High Consideration Customer

  • Cree Lawson, CEO of Arrivalist

Is there a better way to measure the digital behavior of consumers considering a complex or expensive purchase and improve outcomes going forward? Measurement company Arrivalist shared techniques they have used successfully, illustrated with six case studies. Their work has application for both considered and impulse purchase brands.

Member Only Access

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.

Member Only Access

Micro Targeting Can Dramatically Improve Facebook Performance

  • Steve Meester; Newcombe Clark
  • AIG Rapid Learning Lab

The authors describe a series of design experiments used to optimize Facebook targeting and retargeting to buyers of travel insurance. Using different creative for different micro-targets, the authors raised prospecting sales lift by four times and retargeting sales lift by 60%. Additional findings included that age did not determine click thru rate, but under thirty-five and over sixty-four rarely purchased.

Member Only Access