FIN-423 / 3 crédits

Enseignant: Ackerer Damien Edouard

Langue: Anglais

Withdrawal: It is not allowed to withdraw from this subject after the registration deadline.

Remark: MA3 only


Summary

The objective of this course is to acquire experience in financial machine learning by solving real-world problems. Different groups of students will work on different industry projects during the semester. Lectures will discuss best practices and tools.

Content

Projects:

  • from local industry partners (bank, market maker, broker, asset manager, etc.)
  • working in different asset-class (commodities, crypto-currencies, equity, FX, etc.)
  • with distinct applications (trading signal, portfolio optimization, volatility prediction, factors extraction, etc.)
  • each group of students will work on one dedicated project during the semester

Machine learning:

  • review of standard methods (regularized linear regressions, tree methods, neural networks)
  • study the challenges of applying data-driven algorithms in finance
  • present various use-cases in financial engineering (model pricing and calibration, time-series simulation, etc.)
  • transform text as data using natural language processing tools
  • discuss selected advanced topics in reinforcement learning (e.g. derivatives hedging)

Keywords

  • finance
  • machine learning
  • projects

Learning Prerequisites

Required courses

  • Programming knowledge of Python
  • Basic probability and statistical knowledge
  • Basic knowledge of finance
  • Basic knowledge of machine learning

Recommended courses

  • Introduction to finance
  • Financial econometric
  • Derivatives
  • Investments

Learning Outcomes

By the end of the course, the student must be able to:

  • Choose an appropriate model to solve a problem in finance
  • Assess / Evaluate and benchmark a model performance
  • Design flexible models for financial applications
  • Implement data processing and models in python code
  • Develop a fast system to replace slow numerical methods
  • Manipulate and transform data

Transversal skills

  • Manage priorities.
  • Make an oral presentation.
  • Write a scientific or technical report.
  • Demonstrate a capacity for creativity.
  • Take feedback (critique) and respond in an appropriate manner.
  • Continue to work through difficulties or initial failure to find optimal solutions.
  • Demonstrate the capacity for critical thinking

Teaching methods

  • Lectures, 2 hours per week for 14 weeks
  • Project sessions, 1 hour per week for 14 weeks

Expected student activities

  • Actively participate to the lectures and the presentations

Assessment methods

  • Class participation 20%
  • Project presentations 20%
  • Project report 60%

Supervision

Office hours Yes
Assistants Yes
Forum Yes

Dans les plans d'études

  • Semestre: Automne
  • Forme de l'examen: Pendant le semestre (session d'hiver)
  • Matière examinée: Financial machine learning projects
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 1 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Automne
  • Forme de l'examen: Pendant le semestre (session d'hiver)
  • Matière examinée: Financial machine learning projects
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 1 Heure(s) hebdo x 14 semaines
  • Type: optionnel

Semaine de référence

Cours connexes

Résultats de graphsearch.epfl.ch.