Data is all around us and can be used to predict the future; some examples are human behavioral patterns, the weather, as well as financial data. In this series of iPython notebooks we'll learn how to extract technical indicators from historical stock data, how to create features and targets out of the data. Then we'll prepare our features for linear, tree-based, gradient boosted, and neural network models. We will use these models to predict the future prices of stocks. Last, we'll cover how to evaluate the performance of the models we train so we can optimize and readjust them. The end goal is to be able to make predictions that have enough accuracy to make a stock trading strategy profitable.
Please See the following links for accompanying Google Slide presentations:
This class was created by Will McCormack.