A date fixe
1. Introduction: Data Science
1.1. Applications and examples in Finance
1.2. Brief overview of methods
2. Exploratory Data Analysis
2.1. Histograms
2.2. Theoretical and Sample Moments
2.3. Theoretical and Sample Quantiles
2.4. Hypothesis testing (t-test, p-value)
2.5. Testing for Normality
2.6. Application: Empirical Characteristics of Historical Stock Index Returns
3. Multiple Linear Regression and Related Topics
3.1. Simple regression model
3.2. Statistical properties of regression
3.3. Multiple regression (omitted variable bias, multicollinearity)
3.4. Regression with dummy variables
3.5. Model Validation and Selection
3.6. Caveat 1: Nonstationarity and Spurious Regression
3.7. Caveat 2: Outliers and Overfitting
3.8. Application: Can Yield Curve Information Help Predict Equity Index Returns?
4. Models with Binary Dependent Variables
4.1. Motivation and Introductory Example
4.2. Likelihood-Based Parameter Estimation
4.3. Hypothesis Testing, Model Selection, and Goodness-of-Fit Assessment
4.4. Application: Loan Default Predictio
5. Smoothed Bootstrap
5.1. Simulating the Sampling Process: The Smoothed Bootstrap
5.2. A Multivariate Extension of the Smoothed Bootstrap
6. Statistics with Python
6.1. Packages in Python for probability distributions and statistics
6.2. Descriptive Statistics + Statistical Plots in Python
6.3. Hypothesis testing in Python
6.4. Regression in Python
1. Introduction to AI
1.1. Overview
1.2. A Brief History of AI
1.3. Anatomy of an AI Problem
1.4. Decision Trees and Random Forests
1.5. Working with sklearn
2. Tabular Data and Gradient Boosting
2.1. Feature Engineering in Tabular Data
2.2. Gradient Boosting
2.3. Model Evaluation and Validation
2.4. Working with XGBoost
3. Introduction to Neural Networks
3.1. Fundamentals of Neural Networks
3.2. Mathematics of the Architecture
3.3. Backpropagation and Activation Functions
3.4. Working with Keras
4. Convolutional Neural Networks and Computer Vision
4.1. Understanding Convolutional Neural Networks
4.2. Data Augmentation in Computer Vision
4.3. Transfer Learning with CNNs
4.4. CNNs in Keras
4.5. Generative Diffusion Models and the Future of Computer Vision
5. Reinforcement Learning
5.1. Markov Decision Process
5.2. Q Learning and Deep Q Learning
5.3. Policy Gradient Methods
5.4. Real-world Applications of Reinforcement Learning
5.5. Implementation in Python
6. Natural Language Processing
6.1. Encoding Text into Numbers
6.1.1. Bag of Words
6.1.2. TF-IDF
6.1.3. Word2Vec
6.2. Legacy Architecture: LSTMs
6.3. Attention Mechanisms in NLP
7. Transformers
7.1. Introduction to Transformer Architecture
7.2. Comparison of Transformer Models
7.3. Fine-tuning and Training Transformers
7.4. BERT, T5, and GPT
7.5. Working with Huggingface Transformers
8. Large Language Models
8.1. Creating LLMs
140 heures d'activités pédagogiques.
Anglais
Dr Nathalie PACKHAM, Enseignant chercheur en mathématique appliquée à la finance (http://www.packham.net/)
Examen écrit / Soutenance orale
Prochaine rentrée : 27 novembre 2025
5900 € HT - 7080 € TTC
Entreprise
Particulier
Cette formation est accessible aux personnes en situation de handicap. Une prise de contact avec notre référent handicap permettra d'établir un diagnostic des difficultés potentielles et de mettre en œuvre des mesures d'adaptations. Vous pouvez prendre contact par email avec notre référent handicap à l'adresse : agoyer@sfaf.com
Adresse : 5-7 Avenue Percier à 75008 PARIS
Station « Miromesnil »
Station « La Boétie»
Station « St Philippe du Roule »
Station « Haussmann – Miromesnil »
n°8 025 au 39 rue de Miromesnil
Accès rapide à PARIS et au Bd Périphérique, à l’A86, l’A1 et l’A15
- Parking Zenpark - 55 rue de la Boetie - Paris 8ème Arr
- Parking Haussmann Berri - 155 Bd haussmann - Paris 8ème Arr
![]() |
Antoine GOYER Directeur formation Tél. 06 42 02 37 51 email : agoyer@sfaf.com |