Welcome to the Tecton blog
Our thoughts on extracting ML signal from the data noise
Serving 100,000 feature vectors per second with Tecton and DynamoDB
There is a class of Machine Learning models that require real-time data to make predictions – the process by which these models make predictions is known as Online Inference. Examples of these types of models are models that detect fraudulent … Read More
Introducing Array Type Features
We’re excited to announce that Tecton now natively supports Array type features. Our customers are now deploying array features in operational ML models. In this article, we’ll go through (1) how arrays are commonly used in operational ML systems and … Read More
Tecton’s Security and Compliance Journey to SOC 2 Type 2
Tecton is SOC 2 Type 2 compliant (but that’s not what this post is about) If you search for “SOC 2 Type 2 announcement” you’ll find troves of blog posts from companies of all sizes, so that’s not what this … Read More
My observations since joining Tecton as VP of Engineering
I joined Tecton 4 months ago and would like to share my impressions while they are still fresh! I have spent almost 2 decades in various startups. In seven of them I was Director of Engineering and later VPE in … Read More
Samantha Rydzewski
We are happy to announce a new blog series here at everyone’s favorite feature store – Featured Tectonauts . In this blog series, we will be highlighting the amazing characters we get to interact with daily here at Tecton. Want … Read More
Introducing Low-Latency Streaming Pipelines for Real-Time ML
Intro We’re excited to announce that Tecton now automates low-latency streaming pipelines, to help organizations quickly and reliably build Real-Time ML models. Real-Time ML means that predictions are generated online, at low latency, using real-time data; new events are reflected … Read More
Journey to Real-Time ML
Intro We speak with hundreds of enterprise ML teams every year. And we’ve observed a typical pattern for the adoption of ML in the enterprise. Not every organization follows the exact same steps, but we’ve seen the pattern validated enough … Read More
apply(meetup): Announcing the Speaker Lineup for August 11
Here we go again! It seems like just yesterday we were hosting the first iteration of apply(). Now back by popular demand, we’re hosting apply(meetup) on August 11th from 9am to 12pm Pacific Time … Read More
apply() Highlight: How to Use Fast & Fresh Features for Online Predictions
Online inference can significantly increase the impact of a machine learning model by incorporating fresh data. For example, if we’re building product recommendations for an e-commerce site, our model will benefit from information about what other products the user recently … Read More