About
Summary
The Fin-ML/IVADO Workshop is a one-week practical training in machine learning, applied to concrete problems in finance and insurance. This workshop will consist of theory in the morning, followed by problem-solving workshops in finance and insurance in the afternoon.
The workshop will be held in English. Participants will have to bring their laptops for the practical part, no special installation is required.
Objectives
- Train professionals in new technologies in data science, machine learning and operations research;
- Develop an understanding of the challenges and issues of data science applied to a specific field;
- Learn to use computer tools to solve concrete problems;
- Foster knowledge sharing and facilitate networking among specialists in a particular field;
- Encourage interdisciplinary knowledge sharing.
Prerequisites
Basic knowledge of mathematics and programming (ideally Python) is strongly recommended.
Organizers
- Manuel Morales, Université de Montréal
- Rheia Khalaf, Université de Montréal / IVADO
- Brian Moore, IVADO
Contact
For any inquiries, please contact us at formations@ivado.ca.
Dates and places
Program
Introduction to machine learning
SCHEDULE:
09:00 – 09:30: Registration and light breakfast
09:30 – 12:30: Theory
- Introduction
- Logistic regression and regression: Machine learning vs. statistical approaches
- Types of learning: supervised, unsupervised and reinforced
- Good practices: Overlearning
- Good practices: Cross-validation and experimental design
12:30 – 13:30: Lunch
13:30 – 16:30: Tutorial
- Framework presentation : Python, Keras, Pytorch.
- Some illustrative examples.
Two coffee breaks at 11:00 and 15:00
Supervised and unsupervised learning
SCHEDULE:
09:00 – 09:30: Registration and light breakfast
09:30 – 12:30: Theory
- Introduction : Classification problem
- Traditional approaches : SVM, Random Forests, etc
- Modern approaches : neural networks
- Good practices
- Introduction : Clustering problem
- Traditional approaches : K-means
- Modern approaches : Embeddings
12:30 – 13:30: Lunch
13:30 – 16:30: Tutorial
- Keras Tutorial: Data mining in insurance
Two coffee breaks at 11:00 and 15:00
Neural networks
SCHEDULE:
09:00 – 09:30: Registration and light breakfast
09:30 – 12:30: Theory
- Introduction: Forecasting problem
- Multilayered Perceptron
- Introduction to recurrent neural networks (RNN)
- Good practices
12:30 – 13:30: Lunch
13:30 – 16:30: Tutorial
- Pytorch tutorial: Data mining in finance
Two coffee breaks at 11:00 and 15:00
Introduction to NLP
SCHEDULE:
09:00 – 09:30: Registration and light breakfast
09:30 – 12:30: Theory
- Text processing
- Sentiment analysis
- Application of convolutional neural networks (CNN)
Embeddings and anomaly detection
- Generative models
12:30 – 13:30: Lunch
13:30 – 16:30: Tutorial
- Case study: Spam detection and sentiment analysis
Two coffee breaks at 11:00 and 15:00
Reinforcement learning
SCHEDULE:
09:00 – 09:30: Registration and light breakfast
09:30 – 12:30: Theory
- Introduction: learning by reinforcement
- Q-learning
12:30 – 13:30: Lunch
13:30 – 16:30: Tutorial
- Case study: Reinforcement learning in finance
Two coffee breaks at 11:00 and 15:00