Skip to content
View NathanielCogneaux's full-sized avatar

Highlights

  • Pro

Block or report NathanielCogneaux

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
NathanielCogneaux/README.md

👋 Welcome to my github profile

💼 AI Engineer | Quantitative Researcher
📍 Based in Seoul right now | E-7-1 Visa Holder


Current Interests

• Time Series Forecasting
• Probabilistic Modeling
• Causality and Correlation Analysis
• Tabular data
• Uncertainty Quantification
• Statistical Model Evaluation
• AI & ML for Financial Data
• Trustworthy and Interpretable AI
• Mathematical Modeling
• Dynamic pricing & yield management


Tech Stack

Category Tools & Technologies
Languages Python C# SQL
Frameworks PyTorch PyTorch Lightning scikit-learn Pandas W&B Optuna
Tools Git Linux Visual Studio VS Code Conda
Infra / MLOps MLflow AWS Airflow FastAPI Streamlit Docker

💻 Top Languages by Codebase

Top Langs


Contact

Pinned Loading

  1. Master_Thesis_UQ Master_Thesis_UQ Public

    Introducing a novel lightweight, post-hoc, single-pass, model-agnostic uncertainty quantification model for pretrained deep neural networks, designed for efficiency, scalability, and compatibility.

    Python 1

  2. NLP-comparison-between-Naive-Bayes-RNN-LSTM-and-Transformers NLP-comparison-between-Naive-Bayes-RNN-LSTM-and-Transformers Public

    Comparative study of Naive Bayes, RNN, LSTM, and Transformers (BERT) applied to financial sentiment analysis. Conducted as part of a Master’s degree project using the Kaggle Financial News dataset.…

    Jupyter Notebook

  3. Understanding-Uncertainty-in-Deep-Learning-through-Bayesian-Approaches Understanding-Uncertainty-in-Deep-Learning-through-Bayesian-Approaches Public

    Personal repository exploring Uncertainty Quantification (UQ) in deep learning. Includes theory notes, runnable notebooks, and slides/reviews of key papers covering applications in reinforcement le…

    Jupyter Notebook

  4. Weather_Forecast_Ideas Weather_Forecast_Ideas Public

    Personal project comparing time series models (ARIMA, CatBoost, Random Forest, XGBoost, TFT) for hourly weather prediction. Focused on minimizing MAE for December forecasts across multiple stations…

    Jupyter Notebook

  5. Unbiased-Simulation-of-Stochastic-Differential-Equations Unbiased-Simulation-of-Stochastic-Differential-Equations Public

    Master’s project implementing Henry-Labordère et al.’s unbiased Monte Carlo method to simulate SDEs without discretization bias. Includes a report, code, and notebooks demonstrating theory and expe…

    Jupyter Notebook

  6. Monte-Carlo-Cross-Validation-for-Time-Series Monte-Carlo-Cross-Validation-for-Time-Series Public

    Building Monte Carlo Time Series Cross Validation without replacement, scikit learn ready