Machine Learning in Industry

Overview

The course Machine Learning in Industry introduces students to some of the main machine learning use cases in the Financial Services Industry with an emphasis on Credit Markets and Structured Finance. The students will be taken through the full machine learning life cycle, from data acquisition, collection and analysis to model development, deployment and monitoring.

During five days of hybrid lectures with a strong focus on practical application and coding sessions, the students will be able to:

• Understand key concepts and methodologies in machine learning.

• Connect theory with practical problems through Python programming.

• Familiarize with Data processing techniques for handling heterogeneous and alternative data sources.

• Discover the machine learning industry uses in real-world credit and financial contexts.

• Design and execute a complete machine learning pipeline, from data acquisition and preprocessing through model development, deployment, and monitoring.

  
  

Course Setup and Schedule

Setup

Each day of the training, the students will be invited to hone in on a specific topic of machine learning in industry. They will learn by doing: the training time will be split between lectures and hands on coding sessions where they will be challenged to apply what was taught in order to solve real issues data scientists may come across at various stage of a machine learning industry project.

Students will be split into small work groups with which they will participate in both the on-site practical sessions and the final project course assessment. Due to the hybrid of the event, on-site presence is highly recommended for the best possible experience, although online presence is also possible.

Assessment

The course assessment will challenge students to go through a machine learning project from start to finish on a given dataset related to credit markets and/or structured finance.

Candidates will be assessed based on the group project in a pass/fail way, with the evaluation encompassing the quality of the code (including the documentation), the final presentation and the paper. In case of insufficient project evaluation, a single make up session is provided.

The final assessment will take place approximately 4 months after the end of the course, and will consist of a presentation including Q&A and deep-dive in the codebase. Monthly project-progress meetings will be organized to assess students' progress and address questions they may have.

Course Schedule

Teaching Team and organisation support

Teaching Team

Gennaro Di Brino

Head of Data Science

Cardo AI

gennaro.dibrino@cardoai.com

Tommaso Guerrini

Senior Data Scientist

Cardo AI

tommaso.guerrini@cardoai.com

Stefano Penazzi

Senior Data Scientist

Cardo AI

stefano.penazzi@cardoai.com

Course supported by

CardoAI

Via S. Francesco d'Assisi, 15, 20122 Milano MI

Università degli Studi di Milano

Department of Economics, Management, and Quantitative Methods

Via Festa del Perdono, 7, 20122 Milano MI