From what supervised learning is, to SHAP, K-means, recommenders and forecasting.
Python
scikit-learn
pandas
NumPyThe core of this platform. Chapters in order: what a model actually learns, how to split data without lying to yourself, how to train and evaluate, the five algorithm families industry actually uses, how to explain why the model decided what it did, learning without labels, and then the two applications most often asked for at work: recommendation systems (demographic, content-based, collaborative) and time-series forecasting (exponential smoothing, ARIMA, Prophet). Every chapter has something you can drag, because a KNN boundary at k = 3 versus k = 25 is something to be seen rather than read about.
Read a free lesson: Supervised, Unsupervised, ReinforcementEvery module and lesson in this track. Lessons marked free are open to everyone; the rest open once you own the track.
Every lesson in this track, with summariesThree kinds of learning, and the two data distinctions that drive almost every later decision.
Before any algorithm. A bad split produces a beautiful number that lies.
How to train, how to measure with the right metric, and the one trade-off that explains nearly every model failure.
The algorithm that learns nothing, and teaches a great deal precisely because of that.
Find the boundary with the widest gap to both classes. Simple, and very strong in high dimensions.
The oldest model, the easiest to explain, and still a baseline that is hard to beat.
Called regression, does classification. And it outputs a probability, which is more useful than a class.
From one tree you can draw, to hundreds that win nearly every tabular competition.
The work that most often decides the result, and is least often covered in tutorials.
Three tools answering three different questions. Using the wrong one gives a confidently wrong answer.
Finding groups without labels with K-means, and condensing many columns into a few with PCA.
Filling the blank cells of a user–item matrix three ways — demographic segments, item features, and similar neighbours — then measuring which one is right.
The real one, from a lesson — it runs in your browser. No account needed.
This track is part of a larger path. Buy the whole path as a bundle and every track in it costs 40% less.
