MODELS AND TECHNOLOGY FOR THE FINANCIAL INDUSTRY

The teaching is one of the characterizing courses of the Master's Degree course in DATA ANALYTICS FOR BUSINESS AND SOCIETY and reviews the machine learning techniques applied to the financial industry.
The course focuses on understanding the most common algorithms and tools used by data scientists in finance.
During the course, practical cases will be discussed in order to apply the acquired knowledge. Python will be used.

1. Knowledge and comprehension
- study and understanding of the data available in the financial industry
- review of the common machine learning techniques applied to the financial industry

2. Application of Knowledge and comprehension
- Identify and apply the machine learning techniques to the analyzed problem
- Analysis of practical cases with the use of Python

3. Judgment skills
- Validation and testing of the model

Follow the requirements indicated by the Master's Degree course in DATA ANALYTICS FOR BUSINESS AND SOCIETY

Introduction to Machine Learning in the financial industry
Unsupervised learning
Supervised learning and regularization (Linear and Logistic regression, survival analysis, and support vector machines)
Financial Portfolio and regularization

Written material will be provided on the Moodle course linked with the lessons.
Suggested reading: Hull, J. (2021). Machine Learning in Business: An Introduction to the World of Data Science. Third Edition. Amazon Distribution.

For attendees: The learning assessment consists of a written part (open questions) and an empirical analysis carried out in a group or individually.
For non-attendees: Written exam.

written

For Attending Students (Written Exam + Empirical Analysis):

A grade between 18 and 23 (Sufficient/Fair) indicates a basic understanding of financial data and Machine Learning techniques. The empirical analysis may show shortcomings in the application of techniques or model validation, and the financial interpretation of results will be weak or absent. Answers to open questions will be essential, but they may contain inaccuracies.

A score between 24 and 27 (Good) reflects a good understanding of financial industry data and applied Machine Learning techniques. The empirical analysis will demonstrate correct application of techniques with adequate model validation, and results will be interpreted with clear, though not always in-depth, financial relevance. Written answers will be clear and substantially correct.

A grade between 28 and 30 (Very Good/Excellent) denotes a critical mastery of both theoretical knowledge and practical application, with an excellent ability to connect Machine Learning techniques to the financial context. The empirical analysis will be excellent, featuring innovative application of Machine Learning techniques, rigorous testing and validation, and the financial interpretation of results will be profound, insightful, and well-argued. Written answers will be complete, accurate, and demonstrate advanced judgment skills and financial relevance.

For Non-Attending Students (Written Exam Only):

A grade between 18 and 23 (Sufficient/Fair) indicates an essential understanding of financial data, Machine Learning techniques, and their application. Answers will be brief or partially correct, with limited judgment on models and scarce or no interpretation of financial implications.

A score between 24 and 27 (Good) indicates a good understanding of the topics covered, with clear and correct answers on the application of techniques and processes, demonstrating awareness of financial implications.

A grade between 28 and 30 (Very Good/Excellent) reflects an in-depth and critical understanding of the entire program. Answers will be complete, well-argued, and demonstrate an excellent ability to identify and evaluate the most suitable techniques, providing acute and pertinent financial interpretations.

Lecture. Slides, coding activities, exercises and examples available on Moodle platform.

This subject deals with topics related to the macro-area "Human capital, health, education" and contributes to the achievement of one or more goals of U. N. Agenda for Sustainable Development