2016 / Engie
• Machine Learning on electric load curves
Modeling customers' thermo-sensitivity
* Technical environment: Python
2016 / Groupe Renault
• Project Assistance to the forecast of the Italian and English car market
Articles scraping from automotive market web sites
Text mining: Analysis of the online articles.
Stemming, POS tagging, dependency parsing,
Extraction of professional opinions and their projections over time.
Extraction and Annotation of named entities NER & NEA
Participation in the Response to the Tender for proposal Call
Documentation: bibliographic research and implementation of the most recent paper about the feelings analysis
• Project Analysis of opinions on the diesel market
Natural Language Processing: Analysis of feelings and opinions
Dataviz: graphical presentations of the results
* Technical environment: Python, Neo4j, Java, CoreNLP, NLP, NLTK,
2016-2017 / Lexis Nexis
• Project of Jurisprudence Documents Rapprochements
XML documents parsing
Extraction and choice of features , features reduction
Machine learning algorithms application: documents rapprochement, cosine similarity and KNN
* Technical environment: Python, scikit-learn, java, spark MapReduce and spark MLlib
2016-2017 / Nature et Découvertes
• Crowfunding and product recommendation
Preparation and data analyzes
Data processing, recommendation, textual data rapprochement
Dashboard, visualization, parallelization.
Development, Big Data architecture.
Natural Language Processing
* Technical environment: Python, scikit-learn, Nifi, Kibana, Elasticsearch.