AMASES Summer School 2024

AMASES

and

SoBigData++

jointly organize the

SUMMER SCHOOL IN

Machine learning methods for finance

July 14-19, 2024

Bertinoro (Forlì-Cesena), Centro Residenziale Universitario

 

AIM OF THE SCHOOL

The aim of the school is twofold. First, it aims at presenting a comprehensive view of the theoretical aspects of machine learning methods, including neural networks and advanced deep learning models, signature of a stochastic process, reservoir computing, and reinforcement learning. The second aim is to present the effectiveness of such methods in quantitative finance, including pricing, volatility forecasting, risk management, and financial trading. A key highlight of the program is the emphasis on practical applications. Hands-on workshops and tutorials in Python will constitute a significant portion of the program, allowing participants to apply theoretical concepts to data.

 

SPEAKERS

  • Marco Corazza (Università Ca’ Foscari, Venezia) – Basics of Reinforcement Learning for financial applications
  • Blanka Horvath (University of Oxford, UK) – TBA
  • Giulia Livieri (London School of Economics, UK) – Reservoir computing for time series analysis
  • Piero Mazzarisi (Università di Siena) – Crash course on artificial neural networks
  • Sara Svaluto Ferro (Università di Verona) – Advanced probability and machine learning techniques for mathematical finance

 

EDUCATIONAL GOALS

The summer school aims to provide knowledge and practical experience in a number of topics:

  1. Models of artificial neural networks, dealing with theoretical aspects (universality, backpropagation, backtesting), advanced solutions (deep learning), and empirical applications to financial datasets (Python implementation of methods and training algorithms);
  2. Neural network-based approach for pricing and calibration of volatility surfaces, applicable throughout a range of volatility models, including stochastic volatility models and the rough volatility family, and a range of derivative contracts;
  3. Reservoir computing paradigm within the framework of recurrent neural networks, dealing with theoretical and computational aspects (displaying clear advantages with respect to other recurrent neural network models), with applications to time series analysis;
  4. The concept of signature of a stochastic process, its theoretical properties (algebraic properties, moment formula, universal approximation theorem), and its applications for pricing of classical and VIX options;
  5. Reinforcement learning algorithms as a solution of dynamic optimization problems (Bellman equation), with a focus on recurrent reinforcement learning, applied to trading and other financial problems.

 

IMPORTANT DATES

  • 5th June: application deadline (limited availability on the basis of CV)
  • 9th June: notification of acceptance
  • 14th 20th June: DEADLINE EXTENDED for registration and payment

 

HOW TO APPLY

Send your candidature along with your CV to summer.school.amases2024@gmail.com

 

PROGRAM FEE (accommodation – single room – and all meals included)

€600 + 26 for scholars, non-AMASES members (includes AMASES membership)

€600 for scholars, AMASES members

€1200 for practitioners

 

PAYMENT

For the payment please follow the link:
https://www.ceub.it/events/event/amases-summer-school/?lang=en

 

RENOUNCE AND REFOUND:

To submit a renouncement and ask for a refund, please send an email to summer.school.amases2024@gmail.com.

After the payment, you can submit your renouncement up to one week (7 days) before the beginning of the course and ask for a motivated refund. In case of reimbursement, 150 EUR will be deducted for administrative costs.

Over the terms for refund (less than 7 days from the beginning of the course) you need to provide your request with supporting documentation, which will be submitted to the AMASES Scientific Committee.

 

PROGRAM

AMASES Summer School 2024 brochure (97 downloads)

 

ORGANIZERS

  • Giacomo Bormetti, University of Pavia, giacomo.bormetti@unipv.it
  • Piero Mazzarisi, University of Siena, piero.mazzarisi@unisi.it
  • Manuel Naviglio, Scuola Normale Superiore, manuel.naviglio@sns.it
  • Giorgio Rizzini, Scuola Normale Superiore, giorgio.rizzini@sns.it
“European Program scheme “INFRAIA- 01-2018-2019: Research and Innovation action”, grant agreement 871042 “SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics”, www.sobigdata.eu