Skip to content
View OJules's full-sized avatar

Block or report OJules

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
OJules/README.md

👋 Hi, I'm Jules!

🎯 Data Scientist | Aspiring PhD Researcher | Uncertainty Quantification Expert

Transforming uncertainty into actionable insights through advanced statistical modeling and machine learning

🌍 Basé à Neuchâtel, Suisse
🎓 Formation Internationale : Master Statistics (Suisse) + Master MIASHS/AI (France)
🔬 Recherche : Conformal Prediction, Domain Adaptation, Medical AI


🛠️ Tech Stack & Expertise

Core Programming

Python R SQL

ML & Data Science

TensorFlow PyTorch Scikit-learn Pandas

Specializations

  • 🎯 Uncertainty Quantification (CRC, K-CRC, sem-CRC)
  • 📊 Statistical Modeling & Time Series Analysis
  • 🏥 Medical AI & Computer Vision
  • ⚖️ Fairness in AI & Imbalanced Data
  • 👨‍🏫 Mathematics Education & Tutoring

🔥 Featured Projects

Advanced uncertainty quantification for medical AI

  • Implemented CRC, K-CRC, and sem-CRC algorithms
  • 15% improvement in uncertainty model accuracy
  • Complete Python pipeline with automated benchmarking

ML models that adapt across different domains

  • Transfer learning techniques for domain shift
  • Real-world applications in various sectors

Ethical AI with bias mitigation strategies

  • Advanced sampling techniques
  • Fairness metrics implementation

Predictive modeling for mental health outcomes

  • Statistical analysis with social impact
  • Privacy-preserving techniques

📈 GitHub Analytics


🎓 Academic Background

🎯 Master's MIASHS (ML/AI) - Université Lyon 2, France (2024-2025)
Thesis: "Conformal Risk Control for Semantic Uncertainty Quantification in CT"

📊 Master's Statistics - Université de Neuchâtel, Switzerland (2021-2023)
Thesis: "Statistical Efficacy Study of Prevention Campaigns in Switzerland"

🔢 Bachelor Mathematics - Université Internationale de Grand Bassam, Côte d'Ivoire (2017-2020)
Thesis: "Decision Tree: Classification and Regression Cases"


💼 Professional Experience

  • 🔬 Data Scientist - AI Research @ Université Lyon 2 (2025)
  • 📊 Statistical Research Analyst @ LIVES Institute, UNIL (2022)
  • 💼 Data Analyst & Product Designer @ Assurland Africa (2021)
  • 🎯 Project Manager @ ESN Neuchâtel (2023-2025)
  • 👨‍🏫 Mathematics Tutor @ Anacours (2025)
  • 📚 Mathematics Tutor @ Université Internationale de Grand Bassam (2019-2020)

📫 Let's Connect!

LinkedIn Email GitHub


🌟 Fun Facts

  • 🇨🇮🇨🇭 Multicultural background (Côte d'Ivoire ↔ Switzerland ↔ France)
  • 🎸 Music enthusiast who codes to jazz
  • 📚 Always learning - currently diving deep into medical AI
  • ☕ Coffee-powered statistical modeling sessions

"Making uncertainty certain, one algorithm at a time"

Popular repositories Loading

  1. Applied-Optimization Applied-Optimization Public

  2. Network-Analysis Network-Analysis Public

    Advanced network analysis of scientific publications combining textual information and relational structure with machine learning techniques

    Jupyter Notebook

  3. Domain-Adaptation-ML Domain-Adaptation-ML Public

    Advanced domain adaptation techniques for robust machine learning across different data distributions

    Python

  4. Fairness-and-imbalanced-data Fairness-and-imbalanced-data Public

    Advanced techniques for ethical AI development, bias mitigation, and handling imbalanced datasets in machine learning

    Python

  5. MentalHealth-Prediction MentalHealth-Prediction Public

    Ethical approach to mental health screening using privacy-preserving machine learning for clinical decision support

    Python

  6. Conformal-Prediction-Housing Conformal-Prediction-Housing Public

    Advanced conformal prediction implementation for regression with uncertainty quantification on California Housing dataset

    Jupyter Notebook