Resources
The Tecton library of information on feature stores, technology, use cases, and reference architectures.
Videos
Scaling Real-Time ML at Cash App with Tecton
Hear Cash App’s journey through various generations of its core machine-learning capabilities and how Tecton’s real-time feature platform helps them deliver world-class recommendations.
Videos
Real-Time Machine Learning for Financial Services
How Tide built real-time fraud detection and loan approval ML applications using Tecton’s feature platform
Videos
Enabling rapid model deployment in the healthcare setting
Discover how Vital powers its predictive, customer-facing, emergency department wait-time product with request-time input signals and how it solves its “cold-start” problem by building machine-learning feedback loops using Tecton.
Videos
Workshop: Operationalizing ML Features on Snowflake with Tecton
Many organizations have standardized on Snowflake as their cloud data platform. Tecton integrates with Snowflake and enables data teams to process ML features and serve them in production quickly and reliably, without building custom data pipelines.
Tech Talks
Real-Time Fraud Detection with Tecton Streaming Features
Learn how to use streaming and real-time data to optimize your fraud detection models.
Videos
Feature Platforms for Data-Centric AI with Mike Del Balso
In this podcast, Tecton CEO and Co-founder Mike Del Balso joins Sam Charrington to talk about all things machine learning.
Whitepapers
Tecton Security & Compliance
As a service provider responsible for handling sensitive data, we understand that our security program, policies, and controls must meet or exceed our customers’ standards. Data for machine learning (ML) is” often subject to the most stringent legal, regulatory, privacy, Read More
Videos
4 Minute Demo of the Tecton Feature Store Platform
David Hershey from the Tecton team walks through a quick overview and demo of the Tecton Feature Store platform.
Case Studies
Tide Case Study
Tide uses Tecton to accelerate ML model deployment by over 50%, triple the number of features used per model, and save the significant engineering time required to build and maintain an internal feature store.