Machine Learning Use Cases in Finance
- Duration: 3 weeks
- Effort: 20 hours
- Pace: Self paced
In the last six years, the financial sector has seen an increase in the use of machine learning models in financial, banking and insurance contexts. Data science and advanced analytics teams in the financial and insurance community are implementing these models regularly and have found a place for them in their toolbox.
The success of machine learning, and in particular deep learning in image recognition and natural language processing applications, has created high expectations and their use has rapidly spread to many different areas. The financial sector is no exception and the last six years have seen an increase in these types of models in financial, banking and insurance contexts. Data science and advanced analytics teams in the financial and insurance community are implementing these models regularly and have found a place for them in their toolbox.
In this course, we will first present a review of some of the applications of machine learning and deep learning. We will then illustrate their use in financial applications through concrete examples that we have seen have sparked interest in the industry. Our examples will illustrate how we can add value through ad hoc construction of architectures rather than a simple exercise of replacing classical models with more complex ones, such as multi-layer networks.
We will see applications:
- Neural network architectures on graphs to integrate new information dimensions in financial markets and bitcoin transactions;
- Portfolio design using reinforcement learning; and
- Natural Language Processing and information extraction methods from financial disclosures in the in an ESG and sustainable finance context;
This course was developed by IVADO and Fin-ML as part of a workshop that takes place yearly in Montréal, since 2018. You will be accompanied throughout and given concrete examples by six international experts from both Academia and Industry.
The course is primarily intended for industry professionals and academics with intermediate knowledge of mathematics and programming (ideally Python). Graduate students in data science and quantitative finance (mainly those who are not yet familiar with machine learning and deep learning) may find this content instructive and compelling. The content of this course will also be of great use to whomever uses or is interested in AI, in any other way. Previous experience in the financial industry is not necessary to follow this course.
We estimate that it takes 3 weeks to follow this class. The course is divided into relevant segments that you may watch at your own pace. There are comprehensive quizzes at the end of each segment to evaluate your understanding of the content.
We welcome you to this special learning journey of Machine Learning Use Cases in Finance!
This course is brought to you by IVADO, Fin-ML and Université de Montréal.
- IVADO is a Québec-wide collaborative institute in the field of digital intelligence.
- Fin-ML is a nationwide network of researchers working at the intersection of data science, quantitative finance, and business analytics.
- Université de Montréal is one of the world’s leading research universities.
What you will learn in this course
At the end of the MOOC, participants should be able to:
- Recognize when and how to use machine learning models according to the business context.
- Apply the best practices of machine learning and in particular of deep learning in a financial application context.
- Identify some models and architectures of deep networks that can be used to solve problems in finance and insurance:
- Graph neural networks in financial markets
- Reinforcement learning in portfolio optimization
- Information extraction and ESG metrics
These are the topics covered in each module
Module 1 - Introduction and Background
1.1 - Challenges and Opportunities
1.2 - Introduction
1.3 - A Foreword
1.4 - Evaluation module 1
Module 2 - Reminder Machine Learning and Deep Learning
2.1 - Machine Learning
2.2 - Deep Learning
2.3 - Evaluation Module 2
Module 3 - GNN in Finance
3.1 - Introduction to Graphs in Finance
3.2 - Learning on Graphs
3.3 - Construction of Graph Convolutional Networks
3.4 - Use Case – Detection of Illicit Bitcoin Transactions
3.5 - Evaluation Module 3
Module 4 - ESG Evaluation
4.1 - Sustainable Finance ESG Investing
4.2 - Natural Language Processing
4.3 - Use Case
4.4 - Evaluation Module 4
Module 5 - Portfolio Design using Reinforcement Learning
5.1 - Introduction to Portfolio Construction Use Case (with RL)
5.2 - Introduction to Reinforcement Learning
5.3 - Common Challenges in RL
5.4 - Use Case
5.5 - Evaluation Module 5
Module 6 - Conclusion
6.1 - Conclusion
6.2 - Satisfaction survey
6.3 - Certificate of achievement
- From Jan. 16, 2023 to Dec. 31, 2023
- From Feb. 13, 2023 to Feb. 2, 2024
Department of Mathematics and Statistics, Université de Montréal
General Director of Fin-ML Network
Member of CRM, IVADO
Director of Development and Partnerships, JACOBB - Centre d’intelligence artificielle appliquée