Transfer Learning: Lessons from Predictive ML for Agentic AI

May 22, 2025

What 10 Years of ML Infrastructure Teaches Us About the Next Generation of AI, and how the MCP-enabled Feature Store will serve real-time context to agents

Thought LeadershipGenAIFeature PlatformsOperational & Real-Time Machine Learning

How Coinbase Builds Sequence Features for Machine Learning

May 13, 2025

How Coinbase productionizes user sequence features with Tecton and Databricks to power fraud and recommendation ML models.

Feature PlatformsFraud DetectionPartners & IntegrationsOperational & Real-Time Machine Learning

How Tecton and Taktile Power Real-Time Risk Decisions at Scale

May 5, 2025

Learn how Tecton and Taktile enable fraud and risk teams to iterate faster, reduce fraud losses, and make more accurate decisions at scale.

Fraud DetectionFeature PlatformsOperational & Real-Time Machine LearningPartners & Integrations

Why Feature Freshness Makes or Breaks Fraud Detection

April 8, 2025

Learn why feature freshness stops fraud. Real-time data catches attacks instantly, while batch systems create windows for more fraudulent transactions.

Fraud DetectionOperational & Real-Time Machine Learning

Understanding the Feature Freshness Problem in Real-Time ML

March 10, 2025

How quickly can your ML system capture and act on recent user signals? For time-sensitive applications like fraud detection and recommender systems, the most recent events are often the most relevant predictive signals. Like a user’s browsing …

Customer StoriesOperational & Real-Time Machine Learning

Fighting Fraud in Real-Time: North’s Journey to Smarter, Faster ML

January 9, 2025

How North built a real-time fraud detection system that processes millions of payments using machine learning. A technical overview of their ML architecture, challenges, and solutions.

Customer StoriesOperational & Real-Time Machine LearningFraud Detection

Simplify Real-Time AI Systems with Amazon SageMaker + Tecton

December 18, 2024

Amazon SageMaker and Tecton streamline AI deployment for real-time applications, enabling faster ROI through automated feature engineering and rapid predictions.

Feature PlatformsOperational & Real-Time Machine Learning

How Good Models Go Bad in Production

December 10, 2024

Ultimately you want your model to make better predictions — which means improving your model accuracy. Model accuracy measures how often a model’s predictions align with the actual values. How well can it reflect the current state of the real …

Feature PlatformsOperational & Real-Time Machine LearningThought Leadership

Why AI Needs Better Context

November 7, 2024

As companies increasingly rely on AI to drive personalized, real-time decisions, the need for robust, fresh context has never been greater. When models shift from development to production, however, they often fail to perform as expected, leading to …

GenAIFeature PlatformsOperational & Real-Time Machine Learning

A Practical Guide to Tecton’s Declarative Framework

June 26, 2024

In this previous blog post, we saw how treating features as code can revolutionize the feature engineering process and bridge the gap between data scientists and engineers. We introduced Tecton’s declarative framework as an abstraction to …

Feature PlatformsOperational & Real-Time Machine Learning

Create Amazing Customer Experiences With LLMs & Real-Time ML Features

September 13, 2023

Did you know connecting large language models (LLMs) to a centralized feature platform can provide powerful, real-time insights from customer events? This post explains the benefits and how you can fit LLMs into production machine learning pipelines.

Thought LeadershipOperational & Real-Time Machine Learning

How Do Real-Time Features Work in Machine Learning?

September 6, 2023

Learn more about real-time ML features and their benefits in this blog post.

Operational & Real-Time Machine Learning