Machine Learning Essentials

About this course

Machine learning is how computers learn to make predictions from data. It powers credit scoring, fraud detection, demand forecasting, recommendations and much more, and it's one of the most valuable technical skills you can have.

In this course you'll follow the full machine learning workflow used by professionals: framing the problem, preparing data, training models, evaluating them honestly and improving them. You'll build a regression model to predict rent, classification models to predict whether a customer will default on a loan, and a clustering model to discover customer groups. You'll learn exactly why accuracy can be misleading, how to spot overfitting, and how to check models for unfair treatment.

Everything runs free in Google Colab with scikit-learn, the most widely used machine learning library for tabular data.

By the end you will be able to

• Frame a business problem as a machine learning task
• Prepare data: features, labels, encoding, scaling and train/test splits
• Train and interpret linear regression models
• Train logistic regression, decision tree and random forest classifiers
• Evaluate models with MAE, accuracy, precision, recall and confusion matrices
• Detect and reduce overfitting using cross-validation
• Group data with k-means clustering
• Build an end-to-end loan default model and check it for fairness

Before you start

Python for AI, or comfort with Python and pandas basics.