Название: Machine Learning for Asset ManagersАвтор: Marcos M. Lopez de Prado
Издательство: Cambridge University Press
Год: 2020
Страниц: 152
Язык: английский
Формат: pdf (true), djvu
Размер: 10.1 MB
Successful investment strategies are specific implementations of general theories. An investment strategy that lacks a theoretical justification is likely to be false. Hence, an asset manager should concentrate her efforts on developing a theory rather than on backtesting potential trading rules. The purpose of this Element is to introduce Machine Learning (ML) tools that can help asset managers discover economic and financial theories. ML is not a black box, and it does not necessarily overfit. ML tools complement rather than replace the classical statistical methods. Some of ML's strengths include (1) a focus on out-of-sample predictability over variance adjudication; (2) the use of computational methods to avoid relying on (potentially unrealistic) assumptions; (3) the ability to "learn" complex specifications, including nonlinear, hierarchical, and noncontinuous interaction effects in a high-dimensional space; and (4) the ability to disentangle the variable search from the specification search, robust to multicollinearity and other substitution effects.
An ML algorithm learns complex patterns in a high-dimensional space with little human guidance on model specification. That ML models need not be specified by the researcher has led many to, erroneously, conclude that ML must be a black box. In that view, ML is merely an “oracle,” a prediction machine from which no understanding can be extracted. The black box view of ML is a misconception. It is fueled by popular industrial applications of ML, where the search for better predictions outweighs the need for theoretical understanding.
Скачать Machine Learning for Asset Managers (Elements in Quantitative Finance)