© 2026 Hashnode
This is the third post in my Google Advanced Data Analytics Certificate series, documenting the TikTok claims classification project. Part 1 covers initial data inspection (Course 1). Part 2 covers ED

This post builds it from the ground up. From the Bernoulli distribution to the Hessian proof to Newton's method to the exact moment the math collapses — no black boxes, no skipped steps. The Hook Not

Introduction: Why I decided to implement Regularization From Scratch After implementing Linear machine learning models. I learned about overfitting, bias-variance tradeoff, and regularization in theory. L1 and L2 penalties existed, and I could explai...

Introduction While working on an Employee Turnover Prediction project, I ran into a confusion that almost every Machine Learning beginner faces: Is L1 the same as Lasso?If yes, why did my classification model break when I applied Lasso?And why does ...

As I continue my data science and machine learning learning journey, I’ve come to realize something important: building models is the easy part, understanding data and translating predictions into decisions is the real skill. Over the past few projec...
