Actualités et agenda
Nos formations
Établissement
Langue d'enseignement
English
Matières
FINANCE
Responsable(s)
A.RUBESAM
Intervenant(s)
A.RUBESAM, D.ERDEMLIOGLU
Présentation
Prérequis
*** ECONOMETRICS FOR ASSET AND RISK MANAGERS (for sub-track ARM) and EMPIRICAL CORPORATE FINANCE (for sub-track Corporate Finance)” ***
Basic statistics and probability
Knowledge of financial markets and products
Econometrics (student must be very familiar with linear regression))
Knowledge of the R software, including at a minimum: reading data from a file; running different regression models; for loops and if-clauses.
Basic statistics and probability
Knowledge of financial markets and products
Econometrics (student must be very familiar with linear regression))
Knowledge of the R software, including at a minimum: reading data from a file; running different regression models; for loops and if-clauses.
Objectifs
At the end of the course, the student should be able to:
1. Describe how machine learning is used in general and in the field of Finance.
2. Compare and explain methods of machine learning such as supervised and unsupervised learning, tree-based methods and dimension reduction methods.
3. Implement several machine learning methods using the software R.
*Additional Assurance of Learning ("AOL") objectives:
LO5B. Construct expert knowledge from cutting-edge information
LO6A. Thoroughly examine a complex business situation
1. Describe how machine learning is used in general and in the field of Finance.
2. Compare and explain methods of machine learning such as supervised and unsupervised learning, tree-based methods and dimension reduction methods.
3. Implement several machine learning methods using the software R.
*Additional Assurance of Learning ("AOL") objectives:
LO5B. Construct expert knowledge from cutting-edge information
LO6A. Thoroughly examine a complex business situation
Présentation
This is a technical course for students looking to deepen their knowledge in quantitative methods applied to finance. The course aims to cover the following:
- what is machine learning: understanding data and making predictions
- supervised vs unsupervised learning
- clasification versus regression problems
- assessing model accuracy
- trade-off between model interpretability and forecasting accuracy
- resampling methods: cross-validation and bootstrap
- regularization in linear models: LASSO, Ridge Regression
- tree-based methods, boosting, bagging and random forests
- dimension reductions techniques
- what is machine learning: understanding data and making predictions
- supervised vs unsupervised learning
- clasification versus regression problems
- assessing model accuracy
- trade-off between model interpretability and forecasting accuracy
- resampling methods: cross-validation and bootstrap
- regularization in linear models: LASSO, Ridge Regression
- tree-based methods, boosting, bagging and random forests
- dimension reductions techniques
Modalités
Organisation
| Type | Amount of time | Comment | |
|---|---|---|---|
| Présentiel | |||
| Cours interactif | 16,00 | Intensive course with access to computer with software R | |
| Autoformation | |||
| Lecture du manuel de référence | 12,00 | Time to study textbook. | |
| Travail personnel | |||
| Group Project | 8,00 | Students will analyze a case study in groups and provide a final report. | |
| Charge de travail personnel indicative | 14,00 | Time to investigate various packages and machine learning tools in R. | |
| Overall student workload | 50,00 | ||
Évaluation
Assessment will be made through a case study where students should implement machine learning methods in R to solve a practical problem.
If time permits, daily quizzes may be applied.
If time permits, daily quizzes may be applied.
| Control type | Duration | Amount | Weighting |
|---|---|---|---|
| Contrôle continu | |||
| Contrôle continu | 25,00 | 4 | 20,00 |
| Autres | |||
| Projet Collectif | 8,00 | 1 | 80,00 |
| TOTAL | 100,00 | ||
Ressources
Bibliographie
James, Witten, Hastie and Tbishirani, 2017. An Introduction to Statistical Learning with Applications in R. -