Theraflu Tracker

Challenge

GSK’s products and solutions help people across Mexico fight the cold and flu season. But the most complex issue is being able to predict the right time to communicate with customers, highlight the problems, and mitigate the risks associated with the spread of the disease - a silent, invisible condition that can slow down the economy and put lives at risk.

Inspiration

Cold and flu season has become a major public health problem in Mexico. In 2018 alone there were more than 23.8 million cases of acute respiratory infections and 500 deaths due to influenza.

Given that artificial intelligence and predictive data modelling has enabled business and industries all over the world to accurately predict future states and influence positive behavioural change in real time, could the creative application of data inspire the most impactful use of messaging as a solution to ultimately save lives?

Idea

We created the GSK Theraflu Tracker, the most accurate predictive model to calculate the risk of flu anywhere in Mexico.

Leveraging eight years of infection data from the National Institute of Epidemiology, we layered in weather data from more than 80 cities, considering over 50 variables such as temperature, weather, humidity, etc. and analyzing word trends in Google searches and geolocating social media activity related to flu symptoms. This enabled us to accurately and efficiently deploy GSK’s Theraflu product messaging and customer experiences across Mexico at exactly the right moment ahead of the approaching disease.

Growth

By using this intelligent and data-inspired approach, we were able to create targeted messages with over 250 versions of our ads in Mexico alone. Our algorithm delivered an unprecedented 97% accuracy in predicting when and where the flu would strike next across Mexico’s 32 federal states. During the campaign our AI-powered advertising, timely deployment and location-specific messaging grew e-commerce sales by over 200%.