Search

Financial Machine Learning

Updated: Sep 28, 2020

"The essential tool of econometrics is multivariate linear regression, an 18th century technology that was already mastered by Gauss before 1794...It is hard to believe that something as complex as 21st century finance could be grasped by something as simple as inverting a covariance matrix"


"...what if economists finally started to consider non-linear functions?"


"An ML algorithm can spot patterns in a 1000-dimensional world as easily as in our familiar 3-dimensional one."


"Econometrics might be good enough to succeed in financial academia (for now), but succeeding in practice requires ML".


Marcos Lopez de Prado (2018) Advances in Financial Machine Learning


AI Data-driven supporting empirical evidence.


Data and relationships among them which we want to discover. useful algorithms to find relationships.


Not everyone can live with a black-box for legal and compliance reasons. Others can live with it if it provides alpha.


Analogy, you don't need to understand special relativity theory and general relativity theory but both are necessary to build navigation systems; how google maps on your iPhone and you can use them without understanding all theories behind it.


You don't need to win every time. You just need a mathematical edge (like the Casinos) and follow the laws of large numbers.



Recent Posts

See All

Dijkstra shortest path algorithm

Word ladder game (change only one letter to go from Fool to Sage): Fool, Pool, Poll, Pole, Pale, Sale, Sage. How? Dijkstra shortest path algorithm

Deep Learning for Algorithmic Trading

Finance is highly nonlinear and sometimes stock price data can even seem completely random. Machine learning and Deep Learning have found their place in the financial institutions for their power in p

Statistical Arbitrage Trading Pairs

What are z score values? A Z score is the value of a supposedly normal random variable when we subtract the mean and divide by the standard deviation, thus scaling it to the standard normal distributi

©2020 by Arturo Devesa.