Hafed Rhouma

data scientist spark (python, scala, r)

Peut se déplacer à Paris, Paris

  • 48.8651
  • 2.3991
Proposer un projet La mission ne démarrera que si vous acceptez le devis de Hafed.
Proposer un projet La mission ne démarrera que si vous acceptez le devis de Hafed.

Localisation et déplacement

Paris, France
Peut travailler dans vos locaux à
  • Paris 20e Arrondissement et 50km autour
  • Paris et 30km autour


Durée de mission
  • entre 3 et 6 mois
  • ≥ 6 mois
Secteur d'activité
  • Banque & assurances
  • Automobile
  • Chimie
  • Energie
  • High tech
+46 autres
Taille d'entreprise
  • 1 personne
  • 2 - 10 personnes
  • 11 - 49 personnes
  • 50 - 249 personnes
  • 250 - 999 personnes
+2 autres


  • E-mail vérifié



Compétences (10)

Hafed en quelques mots

Being a data scientist is not only about having the best scores, the best algorithmic skills, the best models.

Of course, it’s a part of the Job,

But It’s before ALL being able to understand the business, understand the customers you have in front of you, and being able to use all your tools (SQL, algorithms, math) efficiently to help them use the right data to solve their business problem.

Challenger, with entrepreneur mindset, I will help you to take advantage of your data to increase your profits.


Société Générale - Société Générale

Banque & assurances

Data Scientist

Paris, France

mars 2017 - Aujourd'hui

Contributions and achievements:

• Customers Mail Classifications: Word2vec Features, stemming, lemmatization, stopwords, supervised classification: Clustering classification. POC

• Named Entity Recognition on emails: For GDPR compliance, mail anonymization before storage on Data Lake: CRF vs Bi-LSTM (NeuroNER project) -> 85% Accuracy. On production

• Times Series Modeling on Payment In and Out operations: Decision Tree Regressor, built Dash Interface to visualize the anomalies. On production

• Data Transformation: Migrated a whole info center into Big Data: 2 years of XML files transformed into Hive Tables automated with CronTab, anomalies detections in collected data, SQL queries for end users. On production

• Statistical analysis on Payments Data: Data Quality, Volumes, Customers Segmentation, High/Less valuables customers. Developed a dashboard on these data using API connection to Global Visualization Solution. MVP

• SQL teaching to non-technical collaborators.

• Data exploitability studies: data completeness, data complexity. Best options

• Project Costing Estimation (< 100 man-days)

• Data Scientist community’s contribution: Brainstorming, Papers Presentation, first hand
experiences sharing.

• Contribution to feature team aiming at improving machine learning industrialization
process: CI/CD, conda environment, jupyter hub, Control-M

Recommandations externes


charter modal image

Notre succès est une oeuvre collective

Contribuez à cette réussite et au sérieux de la communauté en signant la charte du freelance Malt.

Signer la charte