This course provides a comprehensive guide on using machine learning to predict stock prices and build a strong stock portfolio. With a focus on Python programming, participants will learn how to calculate technical indicators from historical stock data and create relevant features and targets. The course begins by emphasizing the importance of data preparation for accurate stock predictions. Participants will gain knowledge on how to prepare financial data for machine learning algorithms and apply it to various models, including linear models, xgboost models, and neural network models. Moving forward, the course delves into the use of Python decision trees to predict future stock values and explores forest-based machine learning methods to enhance prediction accuracy. The latter part of the course focuses on scaling data for use in KNN and neural networks, enabling participants to predict future stock values using these tools. Additionally, participants will learn how to plot losses, measure performance, and visualize prediction results. Furthermore, the course highlights the application of machine learning in building an optimal stock portfolio. Participants will gain insights into modern portfolio theory (MPT) and the Sharpe ratio, which are integral to predicting the best portfolios. By the end of the course, participants will be equipped with the skills to evaluate the performance of their machine learning-predicted portfolio. Real-world data sets from NASDAQ will be utilized throughout the course, allowing participants to apply robust theories and techniques to create their own predictions and optimize their portfolios based on their risk appetite and budget.