SIT Learning becomes Constructor LearningRead more

From our founding as Propulsion Academy in 2016 to our acquisition by SIT last year, today we welcome our new brand name: Constructor Learning. Constructor Learning is part of the Constructor Group, initially named Schaffhausen Institute of Technology (SIT). The organization was founded in 2019 by Dr. Serg Bell, a long-time entrepreneur and investor in technology and education. Dedicated to creating knowledge through science, education and technology, the ecosystem combines a comprehensive educational offering that spans the entire learning lifecycle, from K-12 to a private university and executive courses, next-generation research capabilities and commercial activities for technological innovation. Founded and headquartered in Schaffhausen, SIT has rapidly grown since its creation, thanks to organic growth and acquisitions. As it has become a global organization with a footprint in more than 15 countries and a worldwide network of researchers, professors, investors, clients, and alumni, the brand had to be rethought to reflect this expansion better and unify the entire ecosystem under one name: Constructor.

Close announcement
Machine Learning

Applied Machine Learning

Get an in-depth, hands-on experience in solving Machine Learning use-cases from a beginner to advanced level. Learn to define projects and their requirements with a particular focus on quality testing of such algorithms.

Apply now








Program overview

Machine Learning is one of the fundamental blocks of Data Science. Its methods are being actively applied across various industries. The goal of this course is to teach you how to successfully apply Machine Learning to real-world business problems while avoiding common pitfalls.

By the end of the course you will be able to:
  • Convert a business problem into a Machine Learning problem.
  • Define requirements for a Machine Learning project (including key performance indicators) using an ML canvas.
  • Create different types of Machine Learning pipelines (supervised and unsupervised), including data transformation, feature engineering, building a data pipeline, hyper-parameter tuning, loss functions, and cross-validations on several regression and classification tasks.
  • Identify bias and fairness of Machine Learning problems and Machine Learning model explainability and interpretability.
  • Design and solve several real-world Machine Learning use-cases, e.g., predictive maintenance, churn prediction, customer segmentation.

Upcoming dates

Schedule: Mon & Wed, 18:00 - 21:00 (CET), remote

Apply by
Course dates
27. Feb 23
06. Mar 23 - 12. Apr 23
CHF 1'800

What you will learn


End-to-End Machine Learning Pipelines

Day 1: Introduction - Start with how to define a Machine Learning use-case using an ML project canvas and learn about the industry standard lifecycle for Data Science and Machine Learning problems, CRISP-DM. We will then l provide an overview of the major steps of an end-to-end ML pipeline, including defining a base model, defining KPIs of success, different error metrics, model assessment/selection, train-test split, data cleaning, and transformation pipelines, under vs. over-fitting, performance metrics for regression tasks.

Day 2: End-to-End ML pipeline - Building upon concepts from day 1, you will apply feature normalization, missing value imputation, scaling, and selection pipelines. You will work with linear and polynomial regression models and regularization techniques (ridge, lasso, and elastic net).


Classification Models

Day 1: Classification Models - Practice data labeling techniques and applications of Machine Learning algorithms for classification tasks using logistic regression. You will also be working with concepts such as class-imbalance, precision-recall analysis (false positive vs. false negative rates), ROC curves, and the use of the confusion matrix.

Day 2: Advanced Classification Models - Go deeper into Supervised Machine Learning problems using commonly used classification algorithms like K-Neighbors, Naive Bayes, Support Vector, Decision Trees and state-of-the-art Ensemble Learning techniques such as Random Forest, XGBoost and CatBoost.


Unsupervised Learning and Ensemble Models

Day 1: Unsupervised Learning - Along with understanding K-means, hierarchical clustering, and DBSCAN, learn how to apply these models to identify an optimal number of clusters, generate and interpret cluster labels using visualizations and statistics. Another area of focus will be applying dimensionality reduction techniques like Principal Component Analysis and t-SNE.

Day 2: Machine Learning Use Case - Moving back to classification models (now with the power of unsupervised learning), you will apply your skills in a real world scenario. Another focus of this day is to see how unsupervised learning, combined with supervised learning, increases the power of ML systems.


Model Explainability and Selection

Day 1: Model Bias and Explainability Analysis - Most Machine Learning models are biased. We will explore the steps you need to take towards making the model accountable to its results. You will apply visualization techniques to understand model bias and perform model interpretability and explainability analysis using state-of-the-art frameworks like LIME and SHAP. You will also learn about the limitations of these methods and how to identify the effect of confounding factors in such interpretations.

Day 2: Hyperparameter Tuning and AUTO-ML - Though you have been developing and using your own Machine Learning pipelines, on this day, you will learn and apply how to automate most components of the Machine Learning model development and evaluation lifecycle using state-of-the-art AUTO-ML frameworks like PyCaret, TPOT and MLJAR.


Model Deployment, Experiment Tracking and Monitoring

Day 1: ML Model Deployment - Now that we have learned all about model development, it’s time to move on to the next step in the ML process cycle - deployment. You will get familiar with git and version control systems, learn about model deployment strategies, key steps to building and deploying a Machine Learning model on the cloud using AWS as well as locally using a virtual environment.

Day 2: Experiment Tracking and Model Monitoring - Any Machine Learning model needs to be monitored after being deployed in production (even rarely used models need to be quality-checked). During the last lecture day of this course, you will apply statistical techniques to monitor model performance and quantify data drift.


Mini Project

Day 1: Bring your personal project and implement your complete Machine Learning pipeline. We will provide you with suggestions.

Day 2: Continuation and short presentations of final projects.

Weekly schedule















Q&A Session

During these sessions, you are totally free to connect and ask any questions about the covered topics.


Learn from our instructors who are experts in their respective fields and get introduced to new topics during live lectures.


Work on a set of interesting and challenging exercises related to the topics covered in the previous lesson.

Earn a Certificate of Accomplishment

Share your Certificate on social networks, printed resumes, CVs or other documents. Boost your career with the new skills that you gained.


Students say

Vaios Vlachos

Vaios Vlachos

Machine Learning

Right after the course I was able to start working on Machine Learning projects in my company.

Job:Data Scientist at Nispera

Akos Redey

Akos Redey

Machine Learning

It was the best decision I have made by selecting this course over an MOOC at a known global provider.

Job:Senior Business Intelligence Analyst at Wüest Partner

Tools we teach

  • Python

  • Jupyter notebooks

  • Pandas

  • Matplotlib

  • Seaborn

  • Scikit-Learn

  • Auto-ML (TPOT, PyCaret, MLJAR)

  • Evidently

  • Flask

  • AWS


Upcoming events

Attend one of our events. Discover our upcoming workshops, info sessions, final presentations and webinars on trending topics.

  • Data Analytics Workshop

    08. Dec 22, 05:00 PM - 07:00 PM GMT+1

    Location: Online via Zoom

    Join Dipanjan on December 8th from 5 - 7 PM and get an introduction to data analytics. Dipanjan is our lead data science consultant & instructor, leading advanced analytics efforts around Computer Vision, Natural Language Processing and Deep Learning. Dipanjan will lead you through python and data processing basics, talk about framing data science problems, and briefly discuss how to analyze and visualize unique patterns. At the end of the workshop, you will create a model that can predict housing prices using machine learning. If you are interested in data science and data science-related topics, this event is for you. Register today to save your seat.


  • UX/UI workshop with Kenji

    18. Jan 23, 05:00 PM - 06:30 PM GMT+1

    Location: Online via Zoom

    Join Kenji on Wednesday, January 18th, 2023, from 5 - 6:30 PM and get an introduction to prototyping in Figma. Kenji Nguyen is a UX designer at Ginetta, and an expert at designing business applications, custom websites, and mobile apps for leading corporations, ambitious SMEs, and innovative startups. Kenji will be hosting an interactive workshop on prototyping in Figma. This will include wireframing for the initial stages of UX and prototyping in Figma to give a basis for UI. If UX/UI design is something you are interested in exploring further, then this is the perfect opportunity for you! Register today to save your seat.


Empty room with chairs

Application process and prerequisites

This course is suitable for beginners and intermediate Python programmers.
Simply apply to the program here.


How is this course different from other self-paced online courses?

Most self-paced courses are a good place to start. However, they do not go into the depths of problems, people working with Machine Learning face. This course covers that and goes beyond any available Machine Learning training by focusing on both the conceptual and hands-on applied aspects of machine learning. Besides this, the instructors will also share tips, tricks and pitfalls from their industry expertise on machine learning.

How does Constructor Learning’s curriculum differ from other schools?

Constructor Learning has trained more than 500 Full-Stack Engineers and Data Scientists. This has provided the Constructor Learning team an in-depth understanding of what skills are most in-demand in the market and which parts of technology are of highest importance when working with data.

Who should attend this course?

Anyone who wants to gain experience in applying Machine Learning to business problems and learn about the challenges, pitfalls, and best practices of this field. People who want to work on concrete ideas to solve problems or to be able to talk with Data Scientists.

What are the prerequisites for this course?

Programming: The candidate should have beginner to intermediate Python Programming experience. Previous exposure to Machine Learning is not needed. Mathematics: This course deals with applying Machine Learning methods to concrete problems. Basic knowledge of linear algebra and calculus will help you understand the details of Machine Learning algorithms; however, it is not essential to follow this course.

How is the day by day schedule?

Every session, you will learn about a new topic during a 60 to 90 minutes-long lecture coupled with hands-on tutorials. For the rest of the 3 hours, you will train on guided exercises with our teachers and teaching assistants’ help. During Q&A sessions (on Thursdays and 20 minutes before each course), you are totally free to connect and ask any questions on the course and exercises, or for your personal projects.

Is there an interview selection for this course?

No, the goal is to introduce you to the field of applied Machine Learning. Anyone with a background in Python (programming) and basic high school math should be able to follow this course.

Your instructors

Team Member

Dipanjan Sarkar

Lead Data Scientist & Instructor

Dipanjan (DJ) is a Lead Data Science Consultant & Instructor, leading advanced analytics efforts around Computer Vision, Natural Language Processing and Deep Learning. He is also a Google Developer Expert in Machine Learning. Dipanjan has advised and worked with several startups as well as Fortune 500 companies and is also a published author, having authored several books on R, Python, Machine Learning, Natural Language Processing, and Deep Learning. He loves sharing his knowledge with the community to help them grow in their own journey in Data Science.
Team Member

Badru Stanicki


With a Masters in Physics, Badru got into scientific programming and Data Science during his time at the German Aerospace Center in Spain. After working several years in research, he moved into Data Science, first as a student and then as a team member. His main interests are DataOps and Time Series Analysis.
Team Member

Dr. Marie Bocher

Data Science Consultant

Marie has 7 years of experience in developing, deploying, and teaching machine learning and statistical models. At Constructor Learning, she consults companies and mentors individuals on various data science and software engineering topics. She is dedicated to sharing her expertise on these topics with a hands-on, interactive approach to teaching.

Read more about Constructor Learning in our Blog

Read the latest news about Constructor Learning and get informed about all things around Programming and Data Science in Switzerland and Germany.


Data Science capstone projects #19

Published on 02-12-2022 by Ekaterina Butyugina

Read more

SIT Learning becomes Constructor Learning

Published on 28-11-2022 by Claudia Boker

Read more

Full-Stack capstone projects #21

Published on 21-11-2022 by Ruben Villalon

Read more