Historically, measuring the efficiency of creative has been challenging, due to the difficulty in isolating its impact from other factors, such as execution tactics or brand health.
This whitepaper reveals the most efficient ad features from a landmark study in association with Meta, with sector insights too. As brands add more and more creatives that are targeted to increasingly tightly defined audiences into their mix, making sense of what does and doesn’t work best becomes an exponentially complex challenge, with poor links between third party creative test metrics and sales. This study proposes a technical Marketing Mix Modelling (MMM) methodology to help brands understand which creative elements have the biggest impact on marketing effectiveness for them.
We analysed brands in four sectors – automotive, cosmetics, insurance and hospitality – using 3 billion impressions from 2,300 campaigns with almost 23,000 individual creatives across three and a half years, and with a total spend of $8.9m USD.
The 124 models in play encompassed multi-stage econometric modelling, and object and text detection (for example, logos, brand cues, products and copy). Critical to the development of the methodology was the way in which both pre-trained and custom-trained Python models were selected for optimal object and text detection performance.
Join UK GM & Partner, Matt Andrew at 14:20 on Wednesday 26th October at Meta’s annual Marketing Mix Summit to hear more about the study in his talk, ‘Creative insights with MMM: AI & image recognition’. It’s free to register.
Brands can use the methodology to improve efficiencies in execution and the creative process, while supporting creative direction across digital channels.
Thank you for your interest in Ekimetrics. Please fill out the form to ask your question.