Description

I am a highly skilled and motivated Data Scientist with a strong academic background and hands-on experience in artificial intelligence, machine learning, and data analytics. I hold a Master’s degree in Computer Science with a specialization in Artificial Intelligence and Robotics, and I have demonstrated expertise in developing and deploying advanced machine learning models, analyzing large datasets, and creating interactive dashboards for data visualization. My technical proficiency spans Python, TensorFlow, PyTorch, and various data analysis tools, complemented by certifications such as the PL-300 (Microsoft Power BI Data Analyst). I am passionate about leveraging data-driven insights to solve complex problems and improve decision-making processes.

Industry field of expertise

Languages

French
Fluent
Arabic
Native or bilingual
English
Fluent

Workplace preferences

Can work on-site

Paris (up to 50km)

BPCE-IT
Data scientist
TECH
April 2024 - October 2024 (6 months)
Paris, France
During my internship at BPCE Infogérance & Technologies, I analyzed 500,000 internal logs using the DistilRoberta LLM model to identify and mitigate 90% of potential anomalies. I deployed an interactive dashboard to monitor Splunk index volumes, reducing response times by 40%. Additionally, I examined over 1 million authentication logs to detect suspicious activity patterns, improving detection accuracy by 30%. I also developed Splunk dashboards to monitor VM activities, enabling the identification of inactive machines. My work significantly enhanced the company’s operational efficiency and security monitoring capabilities.
Python Machine learning artificial intelligence Deep Learning Splunk IT-Security Microsoft Power BI Scikit-learn Matplotlib Git GitHub
Etis lab
Research assistant
EDUCATION AND E-LEARNING
October 2023 - March 2024 (6 months)
Cergy-Pontoise, France
As a Research Assistant at ETIS Lab, I synthesized four sequential datasets (600 records each) to optimize the performance of RNNs for behavioral pattern analysis. I created a flexible RNN model with adjustable components (LSTM, GRU, Elman) using a modular architecture, achieving 90% accuracy in mimicking human decision-making. I also conducted a comparative analysis of various model configurations, identifying key settings for optimal performance. My contributions advanced the lab’s research in neural networks and decision-making systems.
Machine learning artificial intelligence Deep Learning User Research Data analysis Data Engineer Git GitHub
Ecole Polytechnique
Data scientist
EDUCATION AND E-LEARNING
January 2023 - May 2023 (5 months)
At EMP, I enhanced the CIC-IDS-2017 dataset using SMOTE to address class imbalance, resulting in a 10% increase in detection accuracy. I developed an intrusion detection system (IDS) based on XGBoost, achieving 92% accuracy and outperforming benchmarks such as Random Forest and SVM. I also provided insights into explainable AI using SHAP and LIME, improving the interpretability of the model. My work contributed to more robust and transparent cybersecurity solutions.
Machine learning Deep Learning Xgboost Data analysis Data visualization artificial intelligence Git GitHub