Titre : |
Synthetic financial data generation |
Type de document : |
Mémoire |
Auteurs : |
Daniel GONZALES, Auteur |
Année de publication : |
2019 |
Importance : |
23 p. |
Note générale : |
Pour accéder aux fichiers PDF, merci de vous identifier sur le catalogue avec votre compte Office 365 via le bouton CONNEXION en haut de page. |
Langues : |
Anglais (eng) |
Mots-clés : |
Management FINANCE DE MARCHE ; ANALYSE DES DONNEES ; ANALYSE FINANCIERE ; STATISTIQUES FINANCIERES
|
Résumé : |
The aim of this seminar paper is to compare three methods that can create synthetic data from financial markets data these methods are Geometric Brownian Motion, Bootstrap Methods and Generative Adversarial Networks.Describe how new computational methods like Machine Learning and Artificial methods can help to build stronger models in finance and try to understand why is interesting to consider them as a complement of traditional statistical methods to analyze financial data . Explain how the generation of synthetic data is key to build robust Machine Learning methods Two of the three methods considered in this seminar paper are considered as Machine learning methods , Bootstrap Methods and especially Generative Adversarial Networks that has proven to be successful in generate synthetic data in different application.
Calculations will be made in the open source software Python using NumPy library for an efficient use of linear algebra and Matplotlib library to create graphs. |
Note de contenu : |
PGE: Bibliogr.P. 20-22 |
Programme : |
PGE-Rouen |
Spécialisation : |
Finance de marché - Financial markets, Assets and Risk Management |
Permalink : |
https://cataloguelibrary.neoma-bs.fr/index.php?lvl=notice_display&id=497660 |