Azure Machine Learning in Practice: From Fundamentals to Deployment - with Rafal Lukawiecki

This intensive, 5-day, online, hands-on classroom-style course will teach you everything necessary to prepare your data, build, evaluate, and, most importantly, validate machine learning models, before deploying them to production, using the newest, 2020 version of Microsoft Azure Machine Learning. All with little coding, thanks to the new, highly visual yet powerful Microsoft Azure ML tools. You do not need to have a prior coding experience in any programming language to benefit from this course. You will learn all the fundamentals of machine learning, including the most important algorithms and their performance metrics such as precision and recall, validation charts and curves, like the ROC chart, and much more.

Why attend this class?

Because of Rafal’s 10+ years of real-world machine learning experience. 

You will not only learn all the concepts and tools that you need to know from an experienced teacher who has trained over 900 data scientists world-wide, a highly-respected presenter, capable of holding your attention, but, above all, from a practitioner of machine learning. Rafal Lukawiecki has been delivering ML, data mining, and data science projects for customers in retail, banking, entertainment, healthcare, manufacturing, education, and government sectors for twelve years. Because of that, you will learn:

  • everything essential to starting data science, ML, and AI projects
  • all fundamental concepts
  • how to avoid common pitfalls
  • how to work fast yet accurately
  • what is really useful and practical
  • what is more theoretical but still important
  • what hype you should be wary of

You will be able to ask any questions related to your industry and you will get relevant, pragmatic, no-nonsense answers, helping you get ahead with your own projects. Learn from Rafal who has done it all, not from those who just teach it—this is why it is Practical Machine Learning.

Customer testimonials

What did our students say about Rafal`s last course?

"Rafal er en utrolig dyktig formidler, og kurspresentasjonene var gjennomgående noe av det beste jeg har vært på av kursing."
"Rafal er utrolig dyktig , godt forberedt og hyggelig/ hjelpsom."
"Fantastisk kursholder! Venter med spenning på flere av hans kurs."

Format and hours/delivery components

50% lectures, 30% demos, 20% lab tutorials.

There are 3 delivery components included in this course format:

  • 5 half-day live online lectures by Rafal Lukawiecki, with everyone participating, between the hours of 15:00-18:30 CET). Each session will comprise of a lecture, live demos, and plenty of time to answer any questions.
  • Your own work, taking approx 2–3 hours to complete the labs and assignments, which you are expected to do before the next half-day lecture starts. We will provide you with the necessary data/files and (if needed) Azure VM images that contain a full set-up of all the necessary software that you are expected to run using your own Azure account (free trial is acceptable).
  • Small-group (2–3 students) 50–minute online tutoring sessions with Rafal to review the lab work, to provide course assistance, and to answer any additional questions. These sessions will take place outside of the lecture hours and will match the European or American time zones, as needed. Every student will have an opportunity to participate in 2–3 of those tutoring sessions during the week, and we will be flexible in offering additional one-to-one support for anyone struggling with any aspect of the learning process. We want everyone to succeed!


Analysts, budding and current data scientists, BI developers, programmers, power users, predictive modellers, forecasters, consultants, data engineers, anyone interested in using ML for AI, AI engineers.


There are no prerequisites other than general ability to work with data in any form: if you have used a spreadsheet, tables, databases, or you have written a program, no matter how long ago, you will be able to follow the course.

This course will teach you machine learning using Azure ML: you do not need to understand ML or data science before attending.

About Rafal Lukawiecki

As Data Scientist at Project Botticelli Ltd, Rafal focuses on making advanced analytics and artificial intelligence easy and useful for his clients.

He can help you find valuable, meaningful patterns and statistically valid correlations using data mining and machine learning in data sets both big and small. Rafal is also known for his work in business intelligence, data protection, enterprise architecture, and solution delivery. While majority of his clients come from consumer and corporate finance, entertainment, healthcare, IT, retail, and the public sectors, Rafal has worked in almost all industries.

He has been a popular speaker at major IT conferences since 1998.

Course content - detailed description

We will use the brand-new Azure ML Designer UI, and the completely new Azure ML Studio (very different from the older ones) to teach all the fundamentals of machine learning. You will understand why and how to use specific algorithms, notably: classifiers such as Boosted Decision Trees, Logistics Regression and Neural Networks, both linear and non-linear regressions, clustering, and recommenders. Though almost all of your work will be done using the graphical UI, you will also see how to code for Azure ML Service in Python and in a little R using the most popular Python libraries, such as scikit-learn. Although deep learning is not a focus for this course, you will also see how easy it can be to use it with Azure ML. If you already have some programming experience: that is great—but it is not necessary, as everything needed to use Azure ML, including every line of code, will be carefully explained during the course.

If you are interested in learning R for more advanced ML and data science, please see our other course by Rafal that focuses on R and Microsoft ML and SQL Servers—which we do not cover in this course.

Being practical, we will also show you how to prototype your work using the classic version of Azure ML, which can be faster, cheaper and easier to use, especially on smaller datasets, than the newer version. That may be especially useful during earlier stages of your projects, while you are researching, and before you are committed to them. Conveniently from a learning perspective, the way you work using the visual GUI in both the classic and the new versions of Azure ML is almost the same. Please note, however, that classic Azure ML will only take a very small portion of the course, about an hour—almost all of our time will focus on the new, 2020 version.

You will also learn about Automated ML, which can be helpful at the early stages of machine learning projects, especially while you are still trying to understand the business domain you are modelling, or if the data that you have acquired is confusing or unclear to you. Azure ML provides an easy-to-use interface for rapidly building and evaluating multiple models using AutoML, which you will have a chance to practice using during the course. We will also explain why at the later stages of your project your model reliability will benefit more from relying on your knowledge and experience than from pure automation.

From an operational perspective, you will learn about Azure and non-Azure (other clouds and on-premise) resources needed to support machine learning both during modelling, and later, during the deployment to production. You will see how to consume your models in bespoke apps, processing pipelines, and in analytics tools, such as Power BI, at that stage of your projects. You will learn how to update your models on an ongoing basis—a strength of the new Azure ML service. For those projects where coding is important, whether in Python, R or another language, we will also show you how to set-up brand-new Azure ML Compute Instances, which come with a rich, preconfigured development environment for both data scientists and ML/AI engineers.

Model validity is the most important aspect of any machine learning project. A lot of time has been dedicated to explain it in detail: many validity metrics, such as: precision, recall, AUC, F1 score, accuracy (which is rarely a good metric), and the many charts we use to analyse models, especially: confusion matrix, lift/gain charts, ROC curve, precision-recall curve, calibration charts, scatter plots, and others used for regression evaluation like histograms of residuals.

Above all, this course will not only teach you the technology and how to use it, but, much more importantly, you will understand how machine learning works, how to avoid common mistakes, such as overfitting/overtraining, how to balance model accuracy against its reliability, and how to relate key ML performance metrics to your business goals, making your bosses and clients happy with your progress and results. You will gain clarity how to start your projects and how to finish them. You will understand what types of work are suited to ML, and which are unlikely to deliver results. You will discover what makes good first projects in your own area of specialisation. These are the key benefits of studying machine learning with Rafal Lukawiecki: industry veteran who has been practicing ML, data mining, statistical learning, and data science with his customers for well over a decade, and who has studied artificial intelligence at Imperial College in the ‘90s under the guidance of the leaders and the inventors of this are of industry and science.