Supervised Learning

Key Program Takeaways

Master supervised learning metrics

Learn how accuracy, precision, recall, F1, ROC curves, AUC, and regression metrics work and how to choose the right one for each task.

Improve model performance

Practice model tuning through feature engineering, scaling, encoding techniques, hyperparameter adjustments, and algorithm comparison.

Handle real-world data challenges

Work with imbalanced datasets, optimize thresholds, and apply metric-driven decision-making to select the best model for your business scenario.

Modules Overview

9 Modules

Module 1. Course Overview

Get an overview of the course structure, learning goals, and final project. Understand what to expect, how theory and practice are connected, and how each module contributes to building stronger supervised learning skills.

Module 2. Entry assessment

Evaluate your current understanding of supervised learning through a diagnostic test. You’ll identify strengths and improvement areas and receive personalized recommendations to guide your learning path.

Module 3. Feature Preparation

Explore essential feature preparation techniques used before training supervised learning models. You’ll work with different types of categorical encoding and learn when each method is appropriate.

‍

Outcomes:

Apply One-Hot Encoding to train a logistic regression model and use ordinal encoding to prepare data for decision tree models.
Avoid the dummy variable trap by applying correct encoding strategies.
Compare encoding approaches and select the right method for your dataset.

‍

Tools you will practice with:

Python • Scikit-learn • Jupyter Notebook

Module 4. Classification Metrics

Learn how to evaluate classification models using widely adopted metrics and interpret what each metric reveals about model performance.

‍

Outcomes:

Calculate and interpret true positives, true negatives, false positives, and false negatives.
Build and analyze a confusion matrix.
Use accuracy, precision, recall, and understand the trade-offs between them.
Identify class balance issues and select the appropriate metric for each scenario.

‍

Tools you will practice with:

Python • Scikit-learn • Jupyter Notebook

Module 5. Imbalanced Classification

Dive into techniques for handling class imbalance and improving model fairness and performance in real-world datasets.

‍

Outcomes:

Adjust class weights to improve model behavior on minority classes.
Apply upsampling and downsampling to balance datasets.
Tune and evaluate classification thresholds to improve predictions.
Calculate the AUC to compare models.

‍

Tools you will practice with:

Python • Scikit-learn • Jupyter Notebook

Module 6. Regression Metrics

Learn how to evaluate regression models using the most widely used error and accuracy metrics for continuous targets.

‍

Outcomes:

Prepare datasets and apply metrics to regression tasks.
Calculate MSE and understand its role in error measurement.
Compute and interpret the coefficient of determination (R²).
Evaluate model accuracy using MAE and understand how dispersion affects metrics.

‍

Tools you will practice with:

Python • Scikit-learn • Jupyter Notebook

Module 7. Final Project

Apply all concepts from the course to a real business case: predicting customer churn for a bank based on historical behavior data.

‍

Outcomes:

Prepare and clean the dataset for a classification problem.
Train and compare models to predict customer churn.
Evaluate results using appropriate metrics for imbalanced datasets.
Document your modeling rationale and deliver a data-driven recommendation.

‍

Tools you will practice with:

Python • Scikit-learn • Jupyter Notebook • Project dataset

Module 8. Final Assessment

In this module, you’ll complete the final test—a chance to see how much you’ve progressed, compare your results with the entry test, and get a clear sense of your growth throughout the course.

Module 9. Conclusion

This closing module gives you a quick recap of everything you’ve learned and a space to share your feedback so we can keep improving the learning experience for future students.

Schedule a Consultation

Key Program Takeaways

Who is this program for

Recommended prerequisites

Modules Overview

Get in Touch!