Learn by Source
Johns Hopkins University · on Coursera

Practical Machine Learning

Beginner English SpecializationFREE
SkillsMachine learningRcaret packageModel trainingFeature engineeringModel evaluation

Is this course right for you?

Our take
The machine-learning instalment of Johns Hopkins' popular Data Science Specialization, taught — like the rest of that track — in R.

Good for: ML within the R-based Johns Hopkins Data Science track.

Skip if: You want Python, or you are not doing the JHU specialization.

It centres on the caret package and walks the full model-building workflow: creating features, training models and evaluating them. That tight fit with the JHU track is the deciding factor: if you're on their R-based data-science path it slots in naturally, and if you want Python or a standalone ML course, it's aimed the wrong way for you.

Audit it free on Coursera; a certificate needs a subscription (about $49/month) or Coursera Plus, with financial aid available, and documents the coursework rather than a qualification. Note the R/caret focus is a deliberate choice, not a gap — just make sure it matches your intended toolchain (as of 2026).

Comparison · LBS

Compare alternatives for Practical Machine Learning

Same topic, different options. We surface the trade-offs others hide so you can pick the course that actually fits your time, budget, and goals.
Coursera
Practical Machine Learning
Price
Free
Audit free · Certificate available
Duration
—
Level
Beginner
Certificate
Specialization
Coursera
Machine Learning: Clustering & Retrieval
Price
Free
Audit free · Certificate available
Duration
—
Level
Beginner
Certificate
Specialization
View course →
Coursera
Machine Learning: Classification
Price
Free
Audit free · Certificate available
Duration
—
Level
Beginner
Certificate
Specialization
View course →
Coursera
Machine Learning: Regression
Price
Free
Audit free · Certificate available
Duration
—
Level
Beginner
Certificate
Specialization
View course →
Prices & availability can change — confirm on the provider's site. We're not affiliated with any single provider.

About this course

Practical Machine Learning is the ML course in Johns Hopkins University's popular Data Science Specialization. Taught in R, it centres on the caret package and walks through the model-building workflow — creating training and test sets, preprocessing, fitting a spread of methods (trees, random forests, boosting), and evaluating them.

Browse all AI & ML courses Browse all Coursera courses

Instructor

JL
Jeff Leek
Coursera instructor

Created by Johns Hopkins biostatistics professors Jeff Leek, Roger Peng, and Brian Caffo, whose Data Science Specialization is one of the most-taken on Coursera. The approach is hands-on and R-centric.

Frequently asked questions

R. This is part of Johns Hopkins' Data Science specialization, which is taught entirely in R, so the machine learning here uses R and the caret package rather than Python's scikit-learn. That is important to know: if you specifically want Python-based machine learning, this is not the right course, though the underlying ML concepts transfer regardless of language.

Probably not for the tooling. The concepts — training models, cross-validation, evaluating performance — transfer to any language, so you would not waste your time conceptually, but you would be learning R syntax and R-specific packages rather than Python. If Python is your goal, a Python-based machine-learning course (scikit-learn) is a better fit; take this if you are in the R ecosystem or the JHU program.

It helps. It is course eight in Johns Hopkins' ten-course Data Science specialization, so it assumes the R programming and statistics grounding from earlier courses — particularly R Programming and the statistics courses. You can take it standalone if you already know R and basic ML ideas, but arriving without that R foundation makes it a steep climb, since it does not reteach the basics.

Yes, you can audit it on Coursera and watch the lectures at no cost. The graded assignments and the certificate require a subscription, with financial aid available if you apply. Since the value is in doing the R machine-learning exercises, the paid track is worth considering if you want that hands-on practice rather than only the lectures.

As a single course within the specialization, it typically runs about four weeks at a few hours a week, more if the R or ML concepts are new to you. It is hands-on, so the time goes into actually building and evaluating models in R, with the full ten-course specialization a much longer commitment if you pursue it.
Free
to audit
Enroll now