Patrick Curtis – Applied Machine Learning

This module uses video lessons and 12 exercises to practice exporting and filtering through data using Jupyter Notebook. We will also practice manipulating information by replacing and combining, identifying outliers, and display the data with graphs.

This module uses 4 video lessons to delve deep into regression algorithms, hitting on real relationships, overfitting, and regularization. We will also discuss non-linear relationships and how to model them using decision trees. We then discuss using various ensemble methods.

This module uses video lessons and 11 exercises to go over how to split data into training and testing sets, construct model pipelines, perform hyperparameter tuning, and cross-validate alternative models to find the top performer. Additionally, we will go over how to evaluate models and visualize predictions.

This module contains 3 video lessons to demonstrate how some learning algorithms are used to solve classification problems. By the end of this module, you will be familiar with Characteristics of Binary Classification Problems, Regularized Logistic Regression Models, and Decision Tree Ensemble Classification Models.

This module uses video lessons and 9 exercises to walk through a business case study. We will perform more advanced data exploration and visualization and engineer features based on conditional relationships between existing features.

This module uses video lessons and 8 exercises to continue the business case study from the previous module. We will go over how to use stratified random sampling, the confusion matrix and its advantages over R^2, and go into detail over AUROC. After this module, you would have built a machine learning classifier from start to finish.