Deep Learning Methods in Finance


The course will introduce the general concept of Machine Learning and the whole ML process will be fully analyzed.

At the end of the course the students should be able to:

- Apply preprocessing techniques to raw data

- Understand the concepts of cross-validation, train/test split, leave-one-out

- Understand model evaluation metrics

- Apply regression and classification techniques to build predictive models

- Understand the parameters tuning process

- Apply the Machine Learning process to analyze real financial data

General characterization





Responsible teacher

Mauro Castelli


Weekly - Available soon

Total - Available soon

Teaching language

Portuguese. If there are Erasmus students, classes will be taught in English


No requirements, but basic understanding of programming and statistics are expected.


Introduction to Statistical Learning, Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani

Othe research papers provided by the professor.

Teaching method

Theoretical and practical classes.

Evaluation method

First epoch: Project related to the application of ML techniques to analyze financial data.

Second epoch: Project related to the application of ML techniques to analyze financial data.

Subject matter

Machine Learning: definitions and introductory concepts

The machine learning task: preprocesing, model construction and validation

Evaluation metrics

Cross validation and train/test validation. Model complexity and overfitting

Classification task: logistic regression

KNN algorithm and K-means algorithm

Linear Regression

Support Vector Machines

Random Forests, Decision Tress and Ensemmle techniques


Programs where the course is taught: