In this course we'll give an overview of several applications of machine learning to stock market forecasting (including high frequency trading), beginning with regressions, two "shallow" machine learning models (Support Vector Machines and basic Neural Networks) and ending with a deep learning model (Long Short Term Memory Networks). Each model is discussed in detail as to what input variables and what architecture is used (rationale), how the model's learning progress is evaluated and how machine learning scientists and stock market traders evaluate the model's final performance, so that by the end of the course, the students should be able to identify the main features of a machine learning model for stock market forecasting and to evaluate if it is likely to be useful and if it is structured efficiently in terms of inputs and outputs.

The participant should be familiar with the foundations of statistics, the basics of logistic regressions (desirable), and basic linear algebra (desirable); however, since our course intends to be self-contained, we will provide a review of these concepts as needed. As all the examples of our course come from finance, some familiarity with the Capital Markets and the basic financial concepts is required. A basic knowledge of Python or some other programming language (MatLab, R) is needed, even though the objective of the course is not to learn how to program (shallow and deep) machine learning models from scratch, but rather, to understand how they work and to learn how to adapt them to the particular needs of the user and to optimize their application to stock market forecasting. The math foundations of the basic machine learning models (regressions, neural networks, and support vector machines) will be discussed and followed by a panoramic view of the inputs that are most likely to provide valuable information for stock market forecasting. Standard benchmarking methods used in the industry will be also covered. Subsequently, a number of basic — already programmed — models will be discussed in detail and their performance evaluated.