From multiple siloed campaigns to a customer-centric integrated communication model
Multinational energy companyShell was looking to move from siloed multiple campaigns in the UK to a customer-centric integrated communication model.
To support our client in their mission, we collaborated with EssenceMediacom, as well as Shell’s Data Modelling team and developed a custom-made algorithm.
Our ambition
The client challenged us to launch an always-on integrated campaign supporting and optimizing revenue from all customer shopper missions and 14 product categories across the UK.
Our solution
We revolutionized Shell's Go Well campaign by reengineering their advertising approach. We created a bespoke bidding strategy to for DV360 and Meta to optimze offline sales instead of online metrics. Hosted on Google Cloud, this algorithm allowed for precise targeting based on variables such as time of day, day of the week, seasonality, and a city-specific indicator that factored in diverse purchasing behaviors across different cities.
We also integrated real-time weather data, enabling dynamic adjustments based on temperature, rainfall, and the presence of snow. These enhancements had varying impacts on product categories, with some proving to be more weather-sensitive than others.
The custom algorithm generated over 8,000 tailored ad variants and our bidding algorithm was fine-tuned for optimal performance on Google and Facebook platforms.
The customized algorithm allows for minimum wastage and maximum effect. We can target the right consumer with the right message at the right time and delight them on their digital journey before their physical one to a Shell site.
Claire Cosgrove,
Campaign Manager, Shell UK
Key solutions
A combination of data, predictive analysis, custom-built algorithms, and dynamic creatives
Transactional Predictive Modelling
Integrated Custom Algorithm hosted in Google Cloud
Dynamic Ads
Incrementality Studies – GeoX test
Our results
From a 4-week test period on both Social and Programmatic, we found that our custom algorithms outperformed the platform algorithms previously in place.
1.1% incremental sales uplift per month across 14 product categories
3.6x more likely to visit a store
500,000 store visits in 3 months