The business impact of campaign setup: Reducing media spend through frequency capping optimisation
Abstract
This paper demonstrates the impact of a specific campaign setup best practice — frequency capping — on media performance, highlighting potential cost savings from optimising this setting. Focusing on this single practice, we show how its implementation can improve efficiency and reduce media waste. Analysing thousands of campaigns across DV360 and Meta, we assess whether frequency capping was enabled (compliant/non-compliant) and examine its influence on media spend and reach. An optimised XGBoost model, trained via grid search and cross-validation, estimates media spend based on delivered results. Counterfactual simulations on 500 campaigns show that enabling frequency capping can decrease media spend by 27–38 per cent without negatively impacting outcomes.1 These findings underscore the value of frequency capping as a targeted, data-driven strategy for enhancing advertising efficiency and managing budgets effectively. This article is also included in the Business & Management Collection which can be accessed at http://hstalks/business
The full article is available to subscribers to the journal.
Author's Biography
Maja Kaczkowska is a data scientist at Adfidence, a leading organisation specialising in digital marketing. She studied at the Warsaw University of Technology, where she worked on image analysis projects and was actively involved in academic life, serving as chair of a student research group. She has gained experience working with data in global companies and expanded her marketing knowledge while collaborating with the organisers of the Women in Tech conferences. She specialises in applying statistical methods and machine-learning techniques to evaluate the effectiveness of marketing campaigns. By leveraging data analysis, she optimises costs and enhances the efficiency of digital marketing efforts.
Michał Mirończuk is Head of Analytics at Adfidence, where he leads the analytics team and focuses on turning data into actionable insights that fuel smarter decisions. He is an experienced data science professional and analytics leader with a strong foundation in performance marketing. He first gained expertise as a media buyer and team lead at Project Execution, where he developed a deep understanding of digital media strategy. He then advanced to a key role at Performance Media, focusing on the development of large-scale martech and Big Data solutions, bridging the gap between marketing operations and advanced data systems. He holds a master’s degree in data science from the Polish-Japanese Academy of Information Technology and an engineering degree from Warsaw University of Technology. His work bridges technical depth with business impact, focusing on scalable analytics, machine-learning solutions and marketing technology innovation.
Koen Pauwels is the Associate Dean of Research and Distinguished Professor of Marketing at Northeastern University, and an adjunct professor at BI Norwegian Business School. He has previously worked as Principal Research Scientist at Amazon Ads, where he was responsible for brand building and budget allocation recommendations for hundreds of thousands of advertisers. He received his PhD from UCLA, where he was chosen as one of the Top 100 Inspirational Alumni. After gaining tenure at the Tuck School of Business at Dartmouth, he helped build the startup Ozyegin University in Istanbul. He is Editorin- Chief of the International Journal of Research in Marketing.
Citation
Kaczkowska, Maja, Mirończuk, Michał and Pauwels, Koen (2025, September 1). The business impact of campaign setup: Reducing media spend through frequency capping optimisation. In the Applied Marketing Analytics: The Peer-Reviewed Journal, Volume 11, Issue 2. https://doi.org/10.69554/XDRV8452.Publications LLP