Ritvik Mandyam

Why We Don't Want Leaky Models Here at Factal, we love data. We love machine learning. And, let’s be honest, we love seeing validation scores go up. There’s a distinct dopamine hit when you look at a metric dashboard and see accuracy hovering around 97%, 98%, or even the mythical 99%. For a brief, shining moment last week, we thought we were gods. Our latest batch of models - designed to automate some internal categorizations - weren't just performing well; they were operating at an "Oracle"...

Building an automated data analyst is a lot like being a digital detective. You want to give it a pile of data, walk away to grab a coffee, and come back to a whiteboard filled with "Aha!" moments. But as we learned recently, even the smartest AI can’t find a heartbeat in a mannequin. Here is the story of how Factal Signals  refused to lie to us, and why that makes it the most honest member of our team. What is Factal Signals, Anyway? Factal Signals Before we get into the "drama," let’s talk...

Let’s talk about the specific kind of dread you feel when you open a new database schema for the first time. You know the feeling. You’ve been promised a "structured data warehouse." You have visions of clean Third Normal Form, beautiful foreign key constraints, and column names that actually describe what’s inside them. You fire up your connection, query the information schema, and… Silence. Zero foreign keys. No primary key constraints. Table names like xref_p10_not_deleted  and...