Fundamental Modeling Techniques
About the course
Different business problems require different machine learning techniques. In this two-day badge you will learn and practice with the fundamental modeling techniques that help you to solve most of these problems (continuous, categorical and unsupervised predictions) and provide you with the necessary basis to learn about the more complex models.
Through our interactive and instructor-led exercises, you will gain a full understanding of these fundamental modeling techniques, with significant time spent on validation metrics and interpretability of models. This will include regression models (linear & logistic), decision trees and K-means. All of which you will get to practice in real case exercises alongside our expert trainers. Once you understand the methods, you can begin to make a real impact on your business.
Why this is for you
These models, such as linear regression, are often regarded as simple and something anyone can build. However, in practice a lot of issues (and how to solve them) are not well-known or just discarded, leading to bad models, wrong conclusions, and diminished impact. This course aims to provide a full understanding of the fundamental models with typical issues that you can encounter and solutions for these issues.
Furthermore, understanding the fundamental techniques is crucial for understanding more complex models, such as XGBoost and neural networks, which are often related to the fundamental models.
This course is aimed at all professionals, working hands-on with data and AI, from a data science or data engineering perspective. To follow this course you must have completed our Machine Learning Process (3201) course. If you are a Data Scientist and want to know more, join our program!
What you’ll learn
- To explain and practice with models that are suitable to solve most of the business problems (categorical, continuous and unsupervised predictions)
- To choose and perform the correct validation metrics for these models
- To interpret the output of the models by means of their coefficients or visualization of the output
Theory and practical use
- Linear regression model – Proficient in building and explaining a linear regression model
- Logistic regression model - Proficient in building and explaining a logistic regression model for classification problems.
- Decision trees - Proficient in building and explaining a decision tree model for classification problems.
- K-means - Proficient in building and explaining a K-means model for unsupervised learning.
- Evaluation metrics & model interpretation - Applying different evaluation metrics for continuous and categorical prediction variables (MAPE, AUC etc.) and interpreting model outcomes and relations through model coefficients and visualization.
All trainings in the GAIn portfolio combine high-quality standardized training material with theory sessions from experts and hands-on experience where you directly apply the material to real-life cases. Each training is developed by top of the field practitioners which means they are full of industry examples along with practical challenges and know-how, fueling the interactive discussions during training. We believe this multi-level approach creates the ideal learning environment for participants to thrive.