Flo: Advancing Women’s Health with ML and Amazon SageMaker
The body is often a mystery, and it’s nice when an external source is able to provide expert, evidence-based information about it. Flo App, a holistic health and wellbeing platform that helps women understand their bodies and minds, was built to do just that. Founded in 2015, Flo supports women as they make better informed decisions about their reproductive, physical, and mental health.
And although women’s health has received increased attention in recent years, Flo’s Chief Brand and Communications Officer Kate Romanovskaia points out that there are still barriers female-centered health brands face, including variation among clients. “Each woman is unique and there are no women with identical cycle patterns or body reactions,” says Ms. Romanovskaia. “It’s very hard to build a one-size-fits-all solution for all women in different geographies and with different health conditions.”
In order to address these challenges, the Flo team created a “super app” with menstrual cycle tracking and prediction at the core of the product. Instead of simply combining data from a user’s most recent cycles, Flo uses machine learning to make its cycle length predictions based on the information a user previously logged, including her age, the days of her periods, symptoms, and more. Additionally, Flo has just completed the MVP of a symptom predictions feature and is also now investigating possibilities to use ML for ovulation and fertile window predictions.
Flo also offers a plethora of personalized multimedia content including video courses, articles, stories and more, that users can implement to educate and better understand themselves. The content is reviewed by over 80 renowned health and wellbeing experts to ensure that all of the information is evidence-based and trustworthy. Smart algorithms help pair users with personalized, relevant information. Users also have access to a secret and anonymous community where they can connect over shared experiences, concerns, and questions.
One of Flo’s overarching values is building a safe, dependable, and secure space for millions of women worldwide. “From the moment the company was founded, we have been consistently working to create an absolutely secure product for our users”, says CTO Roman Bugaev. “To that end, AWS gives us and other companies a secure space to store the encrypted data safely.”
While Flo was originally built on a smaller server, they migrated to AWS after realizing they would need more elasticity and a solid infrastructure in order to scale quickly. With a growing number of engineers working with data from Flo’s 165 million+ users, AWS provides a platform that allows them to focus on innovation.
“The data science department specifically relies on Amazon SageMaker for machine learning, leveraging powerful GPU-based machines offered by AWS to train models on Flo’s large user population,” says CTO Roman Bugaev. He also stresses that working with AWS is bidirectional. Flo’s team uses the technology to the greatest extent of its capabilities, and the AWS team responds to their feedback in real time. “It’s great to have a trusted provider who can support us with the best-in-class services. so we don’t need to reinvent them ourselves,” says Bugaev. “It allows us to focus on our core competency, which is improving the health and wellbeing of every girl and woman worldwide.”