This playful phrase recently became an inspiration for the consumer health marketing team at Bayer – the global life sciences company – to create a forecasting model that would, in essence, try to predict the future. Specifically, the team wanted to predict search trends for colds and flu around the world so they could reach users with the right products to relieve their symptoms.
Eric Gregoire, senior vice president and global head of digital media at Bayer, said the project began in Australia ahead of the local 2022 cold and flu season. The prediction model was so successful in improving digital marketing performance that the company wants to expand the initiative globally.
Aiming for proactive predictions
Typically, marketing teams collect and analyze large data overseas chinese in worldwide database sets to find customer trends and then adjust their strategy based on the findings. Bayer wanted to go one step further. “We wanted to make the work less reactive and more proactive so we could predict and anticipate the best way to reach the right consumer with the right content at the right time,” said Gregoire.
The Bayer Australia team started the project in early 2022 by combining data from Google Trends and external open-source data, such as weather and when to use double confirmation climate information, to try to predict specific trends around the cold and flu season in different Australian regions. They started with fairly simple data points, such as real-time temperature and public reports of flu cases.
“The most obvious starting point is always the seasonal categories, as they provide very clear data points,” said Patricia Corsi, director of marketing, digital and sms to data insights at Bayer Consumer Health. “The critical data that is available indicates the beginning and end of the season.”
Predicting colds with predictive models
From there, the team built a prediction model using Google Cloud’s machine learning technology . The model is trained to use the data to predict customer search interest in cold and flu products in specific markets.
This predictive insight helped the Bayer team be more proactive in their marketing planning and strategy.
“The goldmine was in the search data,” Gregoire said. “The most interesting insights came when our partners at Google helped us add additional data points on search trends and other external trends to provide a more detailed picture,” he added.
For example, the model showed that the cold and flu season began in early May in Australia, with more cases than usual for this period. The data indicated a 50% increase in flu cases across the country.