Marketing Mix Modeling (MMM): An interview with Aleksandra Semenenko, Data Science Director & Global lead on MMM at Artefact

Watch the video

Listen to the podcast

Aleksandra Semenenko joined Artefact in 2019. She holds a Master of Science in Data Science and Business Analytics from ESSEC Business School Centrale-Supélec. She has extensive experience in data and transformation in large enterprises and scale-ups in the UK and EU. Her core expertise revolves around bridging the gap between business and data, and pragmatically bringing the value of data into the organization.

Aleksandra recently sat down with Emmanuel Malherbe, ML Research Scientist and Director of the Artefact Research Center, to discuss the Marketing Mix Modeling (MMM) models Artefact has been developing and the major trends she sees emerging with clients today.

Three trends paving the way for the future of MMM

For the last three years, Artefact has been building models to help companies and clients understand the ROI of their media, advertising, and other types of things that grow new types of investments.

“The first trend is solution in-housing: In other words, the internalization of this measurement capability of the code itself,” explains Alexsandra. “The second trend is getting fast results for brands and clients. Brands want to frequently iterate on their measurement and immediately understand the direct response of their activities. “The third trend is adopting an end-to-end approach. Picture yourself as a client; strategic decisions are made by one set of teams, while operational teams work on the ground, receiving real-time business signals. Our goal is to bridge the gap between them in a seamless end-to-end process without losing vital information or insights.” 

1. How does Artefact support MMM internalization? “We work with business teams to find out what clients want to learn about their marketing or sales activities. We offer them our own model-as-a-service available on different platforms.” 
2. How can clients obtain faster results and insights? “We start with a pragmatic approach to provide teams with quick insights, then iterate. Internalization helps as it gives us quick access to the tech stack and the data, so we can make the connection between model updates, results updates, and business implementation very quickly.”
3. How does Artefact’s end-to-end approach work? “We align the global learning agenda with the local learning agenda. We spend time with the business to ensure the results delivered by our MMMs align with other studies the client has done, either with AB tests or other MMMs. Bringing all the insights together is more of an analytical and advisory role, rather than bringing in a bunch of data scientists and building the AI from scratch.”

Aleksandra believes the future of MMM is in efficiency: “Marketing mix modeling will have to become faster, more rigorous, simpler to explain to business stakeholders, and more easily accessible to business analysts. And GenAI is important because it can enable clients to query MMM results and build reports by themselves without necessarily having a lot of technical skills,” she concludes.

Watch the video (or listen to the podcast) to learn more about trends in MMM and gain insights into how companies can strengthen their marketing strategy in 2024.

Watch the video

Listen to the podcast

Visit our website thebridge.artefact.com