Since its launch in 2011, HelloFresh has grown exponentially. The company is now publicly traded, counts more than 8 million active customers, employs 21,000+ people worldwide, and is the biggest meal-kit provider globally. To support its growth, HelloFresh invests heavily in creating machine learning models and delivering trustworthy data products to the rest of the organization.
In 2019, HelloFresh set out to ensure that its data scientists and engineers could quickly discover, understand, and securely access high-quality data to prototype and deliver large-scale predictive data products. The ultimate goal was to build the foundations of a data layer that the company as a whole could trust on its path to automating decision-making across the value chain.
With this in mind, Erik Widman, HelloFresh’s AI Product Management Director, set out on a mission to benchmark the solutions that would, in time, provide infrastructure and tools to allow domain teams to focus on building data products, reduce domain-agnostic complexity, and minimize time to insights.
Benchmarking dedicated feature platforms
To benchmark other providers in the feature store space, as well as compare leading vendors (identified as Vendor 2 and Vendor 3 in this post) and Tecton against each other, the teams picked one of HelloFresh’s machine learning models, broke apart the features, and uploaded them to the different vendor solutions so they could test numerous scenarios and better assess the scores for each listed category.
After adding up all the weighted scores into a total category score for each tool—with the highest possible score of 430—the platform team established that Tecton fulfilled 90% of the feature store requirements compared to 63% and 62%, respectively, for Vendor 2 and Vendor 3.
After selecting Tecton as the best possible feature store component on their path to standardizing the use of data to build reliable predictive products, HelloFresh began rolling out Tecton’s feature platform to its many engineering and data science teams across the organization.
HelloFresh’s MLOps platform, of which Tecton is the foundation at the feature and ETL level, helps the organization better understand and address consumer needs with high-quality machine learning. The platform is intended to make it easier for data scientists and machine learning engineers to create robust pipelines, standardize underlying tools, simplify scaling models across geographies, and reduce the time to put models in production.
HelloFresh and Tecton, in Practice
An example of the company’s ongoing program to democratize access to high-quality machine learning models is the Morpheus use case. Morpheus, HelloFresh’s customer prediction model, is the company’s newest algorithm that uses the latest machine learning techniques to offer weekly customer-level predictions.
Today, HelloFresh has deployed Morpheus, a system that reframes customer profitability with 1,360 different gradient boosting models. Each model is trained in parallel in multiple geographies and time horizons for specific customer segments.
But models are only as good as the data that powers them, and Morpheus depends on the engineering of informative features from the collection and transformation of as much high-quality data as possible. That’s why the teams behind Morpheus are in the process of migrating all of the Morpheus features into Tecton.
Tecton will not only help the teams streamline features from all types of different data sources to power the thousands of models in Morpheus, but it will also help the teams ensure data quality and consistency across environments. Additionally, it will enable the teams to supervise training pipelines’ progress to avoid common ML pitfalls like model drift or training / serving skew.
To find out more about HelloFresh’s data-driven framework to select the right feature solution for their MLOps platform or to read more about Morpheus, check out the full story here.
Interested in learning more about Tecton? Join us for our monthly demo—register here.