Investors flock to fund an AI cornerstone: Feature stores – Marketingwithanoy

“Function Stores”, with their gloomy and opaque name, may not sound like the sexiest subject.

But they are an essential part of the AI ​​systems that businesses – and consumers too – use every day. Therefore, they are attracting more and more attention and investment from risk companies, who see the market opportunities growing in the distant future.

AI systems are made up of many components, including features. Functions are the individual variables that act as inputs to the system. When thinking about features, it can be helpful to visualize a table, where the data used by AI systems is organized into rows of examples (data from which the system learns to make predictions) and columns of attributes (data describing those examples). Features are attributes used to describe each example – for example, an AI spam detection tool might use features such as words in the body of the email or a sender’s contact information.

Working with functions is often an ad hoc process within one AI system. But at the enterprise level, where data science teams are responsible for maintaining tens to thousands of systems, a place to manage and track functions is becoming a necessity.

Enter the feature store, a centralized repository for organizing, storing, and operating the features AI systems rely on. Feature stores, introduced as a concept by Uber in 2017, provide a unified place to build and share features across teams in an organization.

“Feature stores are at the intersection of data and machine learning,” Michael Del Balso, the CEO of, a startup that develops feature store software for businesses, told Marketingwithanoy in an email. †[Feature stores are] an essential part of the ‘MLOps’ stack as they enable data teams to quickly and reliably build high-performance functions using real-time data and deliver those functions into production for real-time inference. They serve as the interface between data and [AI] models.”

Feature stores allow data engineers to go beyond just a database and see statistics about features, including which features have been used, where they have been used, and the impact they’ve had on models. Function stores also transform data, allowing users to aggregate, filter, and add functions without necessarily coding. (Think of merging orders in a restaurant to get the “number of orders in the last 30 minutes” function value.)

Del Balso explains, “Advanced feature storage… automate production pipelines to collect data from batch data sources and real-time sources, transform the data in real-time, and store the data in the offline and online store. [They often also] include built-in monitoring capabilities to monitor pipeline health, data drift, service levels, and more.”

Image Credits:

Feature stores promise to improve collaboration between teams while streamlining the development of AI systems. As the demand for them grows, tech giants and startups like Tecton are developing products to meet the need — and investors are enthusiastically backing them.

Leave a comment