- Docente: Matteo Amabili
- Credits: 3
- SSD: SECS-S/06
- Language: English
- Teaching Mode: Traditional lectures
- Campus: Bologna
- Corso: Second cycle degree programme (LM) in Quantitative Finance (cod. 8854)
-
from Apr 19, 2024 to May 17, 2024
Learning outcomes
The Advanced ML course is geared towards state of the art application of neural network to pricing and market risk problem. The studend will acquire a sound knowledge of the principles underlying Neural Networks and will be guided in a tour of the relevant literature concerning the exploitation of machine learning for pricing of highly exotic products and applications to market risk managment. Altough the approach demands very large scale computing facilities, impossible to be provided to the students, nonetheless students will learn how to design solutions to this type of problem and will gain hands on experience of the methodology on simpler and smaller toy models.
Course contents
The first part of the course is dedicated to the study of Neural Networ:
- Foundamentals of Neural Network
1.1 What is a Neural Network
1.2 Train a NN: backpropagation
1.3 Handling categorical variables
1.4 Tips & trick
The rest of the course is dedicated to application in finance, i.e. for the calibration of model from market data.
- Definition of the calibration problem
- NN to approximate price and volatility surface;
- Use NN as a noise filter for pricing
- Pointwise calibration
- Surface calibration
For this second part is higly recommended to attend to the course "computational finance" held by Prof. Pietro Rossi.
Assessment methods
The final exam will consists of a project.
Teaching tools
- Slides (power point/pdf)
- Selected literature
- Jupyter Notebook and Python Code
Office hours
See the website of Matteo Amabili