Choose, Train and Tune the Right Machine Learning Algorithm

For data scientists, ML engineers, developers and analysts who write basic Python. Learn how the main machine learning and deep learning families work, when each is the right choice, and how to prove it: linear and logistic regression, trees and random forests, bias and variance, bagging and gradient boosting with XGBoost, clustering, feature pipelines, rare classes, metrics, honest cross-validation and tuning, interpretability, neural networks in PyTorch, convolutional and recurrent networks, recommendation, time-series forecasting, anomaly detection, serving with FastAPI and monitoring for drift. Every lesson uses one made-up energy supplier, Jarrowfield Energy, and the course ends with a free hands-on lab on your own laptop where you choose, tune, test and defend a churn model in a written decision note.