This information is indicative and can be subject to change.
Python for optimization and finance
Teacher: Olivier Guéant
E-mail: [email protected]
ECTS: 2.5
Evaluation: projects
Previsional Place and time:
Prerequisites: Good Basic knowledge of Python (this is not an introductory course)
Students must have Python on their computer. Jupyter notebooks will be used in class for pedagogical reasons (in Chrome, PyCharm and through Google Cloud Platform)
Aim of the course:
(i) Getting from a basic level in Python to an intermediate one, i.e. coding in a Pythonic way.
(ii) Knowing the main concepts and tools of numpy, scipy, scikit-learn and graphical libraries.
(iii) Building the basic blocks for portfolio management, option pricing, and classification tasks.
Syllabus:
Courses 1 and 2: Python for asset management
Courses 3 and 4: Python for machine learning
Courses 5 and 6: Python for option pricing
References:
Python for optimization and finance
Teacher: Olivier Guéant
E-mail: [email protected]
ECTS: 2.5
Evaluation: projects
Previsional Place and time:
Prerequisites: Good Basic knowledge of Python (this is not an introductory course)
Students must have Python on their computer. Jupyter notebooks will be used in class for pedagogical reasons (in Chrome, PyCharm and through Google Cloud Platform)
Aim of the course:
(i) Getting from a basic level in Python to an intermediate one, i.e. coding in a Pythonic way.
(ii) Knowing the main concepts and tools of numpy, scipy, scikit-learn and graphical libraries.
(iii) Building the basic blocks for portfolio management, option pricing, and classification tasks.
Syllabus:
Courses 1 and 2: Python for asset management
- data analysis with pandas
- data representation with matplotlib, seaborn and plotly
- portfolio construction using scipy optimization tools: minimum variance, maximum diversification, risk budgeting.
Courses 3 and 4: Python for machine learning
- introduction to scikit-learn (estimators, selectors, transformers, pipelines, …)
- introduction to classical classification techniques
- introduction to some cross-validation techniques and grid search
- use case: MNIST data for image recognitions
Courses 5 and 6: Python for option pricing
- introduction to numpy
- finite difference schemes for option pricing (explicit scheme, implicit scheme, Crank-Nicholson scheme)
References:
- Aurélien Géron. Hands-on Machine Learning With Scikit-learn, Keras, and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent Systems. Second edition, 2019.
- Yves Achdou and Olivier Pironneau, Computational Methods for Option Pricing, 2005.