Open to opportunities

Ginwa Fakih

@ginwafakih

Message

I’m a Data Scientist specializing in knowledge graphs, NLP, and large-scale data-driven machine learning solutions.

France

Message

What I'm looking for

I’m looking for a role where I can build data-driven solutions using knowledge graphs, NLP, and machine learning on large-scale data, contributing to robust pipelines, semantic search, and reliable data governance.

I develop data analysis and large-scale data exploitation solutions centered on knowledge graphs, ontologies, and Machine Learning. My work focuses on predictive modeling, leveraging complex data, and improving data quality, interoperability, and governance through metadata schemas, ontologies, and knowledge-graph-driven approaches.

I’ve built end-to-end pipelines for data processing and evaluation, including semantic similarity search, ranking, recommendation, and clustering/classification. I also conduct research on automatic language processing for semantic web tasks—extracting and analyzing terms from text corpora, and using probabilistic models like Seeded LDA for topic discovery and subject classification.

Experience

Work history, roles, and key accomplishments

Data Scientist (Doctorant)

LS2N Laboratory

Feb 2023 - Sep 2025 (2 years 7 months)

Developed data analysis and exploitation solutions at scale using knowledge graphs, ontologies, and machine learning. Designed metadata schemas and built RDF/OWL-based knowledge graph pipelines, including search, classification, and recommendation using semantic similarity.

Knowledge Graphs Semantic Web SPARQL Python Machine Learning Embeddings Clustering Classification Data Pipelines

Research Intern (NLP)

LS2N Laboratory

Feb 2021 - Jul 2021 (5 months)

Performed automatic language processing tasks on text corpora to extract terms and identify business-related themes for semantic web use cases. Built and applied a seeded LDA probabilistic model for topic discovery/classification and optimized thematic clustering to reduce redundancy.

NLP Topic Modeling (Seeded LDA)RDF OWL SPARQL AWS GCP Docker

Education

Degrees, certifications, and relevant coursework

Université Nantes

Doctorat en Informatique, Informatique (Web sémantique et données liées)

2022 - 2025

Doctorat en informatique spécialisé en web sémantique et données liées. Thèse axée sur l’amélioration de l’interrogation des graphes de connaissances.

Polytech Nantes

Master 2 en Data Science, Data Science

2020 - 2021

Master 2 en Data Science axé sur l’extraction de motifs textuels et séquentiels, l’analyse, le clustering et l’indexation. Inclut aussi la classification et l’apprentissage de représentations, ainsi que les modèles graphiques probabilistes.

Université Libanaise

Licence, Génie électrique et électronique, informatique et télécommunications

2016 - 2020

Licence en génie électrique et électronique, informatique et télécommunications. Formation centrée sur des bases en électronique, informatique et télécommunications.