Corentin Martel
Verified Expert in Engineering
Data Scientist and Machine Learning Developer
Rougemont, France
Toptal member since September 27, 2018
Corentin earned a master's degree in engineering from Arts et Métiers ParisTech. He started coding in Python in 2014 and never stopped. Working as a freelancer since 2016, Corentin specializes in data mining and custom development of machine learning and deep learning-based products. Passionate about data science, he also teaches students in an online MSc program. Corentin enjoys working on new topics and learning from others.
Portfolio
Experience
- Python - 6 years
- Generative Pre-trained Transformers (GPT) - 4 years
- Natural Language Processing (NLP) - 4 years
- Machine Learning - 4 years
- Keras - 3 years
- Data Science - 3 years
- Deep Learning - 3 years
- Recommendation Systems - 1 year
Availability
Preferred Environment
PyCharm, Anaconda
The most amazing...
...thing I've developed is a recommendation algorithm for a B2B eCommerce website with over 30,000 products using recurrent neural networks.
Work Experience
Data Scientist
Earthlink
- Developed an unsupervised recommendation algorithm for an on-demand video platform with over 200 k movies.
- Worked on data cleansing and feature engineering (e.g. identify duplicates movies and staff, and create collections of movies).
- Worked on NLP: description-based similarity in multi-languages.
- Deployed an interactive app to test and optimize the model.
Data Scientist
Corelyo (Freelance)
- Developed an unsupervised image classification algorithm based on image similarities, applied on social network images. The objective was to evaluate the social engagement generated by each type of image, to optimize the social presence of my client.
- Implemented a clustering API for SEO keywords, based on the SERP results of these keywords. The goal was to make connections between keywords that are syntactically very different but of same meaning.
- Designed, for a growth hacking agency, an algorithm to find common traits between prospects and clients and used this to prioritize prospects and find out which product they were most likely to be interested in.
- Worked on an exploratory data analysis on tennis data to discover the importance of the first serve percentage in a game, and more broadly what can give a player an edge. I wrote a report with visualisations and interpretation of my results.
- Worked on various analysis and business intelligence (BI) projects. This included assessing the impact of ads on users of an eShop, creating a complete set of KPI/charts for a CRM editor, and building dashboards for HR indicators.
- Mentored students for openclassrooms and hold weekly student appointments to guide them through their data science journeys.
Data Scientist
Foussier.fr, with Corelyo (Freelance)
- Designed from scratch a recommendation engine for a B2B eCommerce website selling hardware to contractors (30,000 products).
- Analyzed customer behavior to better understand the need and choose the most efficient algorithm. The best algorithm largely depends on the clients: Do they buy the same things each time and are there buying patterns?
- Tested several architectures and models, including an RNN-based deep learning model with embedding; also set up metrics and tried various algorithms and data processing to improve it.
- Set up an API to serve recommendations, using Flask and Docker.
- Implemented a Docker container for retraining the model on a regular basis.
Data Scientist
Doctegestio, with Corelyo (Freelance)
- Implemented a machine learning algorithm for document classification (1.5 million documents to classify in 500 categories).
- Created dataset using OCR (optical character recognition) to extract features from PDF and scans, feature engineering, and cleaning for bad quality scans.
- Tested several models over multiple Agile iterations; we first tried with 10,000 documents in five categories and then we iterated when the model was working.
Data Scientist
Hunter.io, with Corelyo (Freelance)
- Created a dataset of website categories using a Python scraper on a yellow-page website, to collect thousand of websites URLs for each category.
- Tested several NLP pipelines and models to classify new websites based on content, by setting a metrics and working to optimize it over several iterations.
- Deployed the selected model in production using a Flask API and Docker.
Research Engineer
LML
- Developed a Python module for testing materials which enabled PhD students to quickly design custom setups with synchronized sensors, camera, and actuators.
- Conducted some tests on my own and extracted useful data from the measures.
Experience
Website Classification Algorithm
https://hunter.io/companiesThis is currently in production so you can test it in real time via the link attached.
Recommendation Algorithm
https://www.foussier.fr/The website is in French, but the recommended items are the one labeled "Nos clients achètent aussi," below any product.
Education
Master of Science Degree in General Engineering
Arts et Métiers ParisTech - Paris, France
Certifications
Machine Learning
Stanford University via Coursera
Skills
Libraries/APIs
XGBoost, Pandas, NumPy, Scikit-learn, Keras, Matplotlib, SciPy, Natural Language Toolkit (NLTK), OpenCV, TensorFlow
Tools
DataViz, DigDash, Tableau, Seaborn, Jupyter, Plotly, PyCharm, Git, GitHub
Languages
Python, Python 2, Python 3, SQL
Frameworks
Flask, Streamlit
Platforms
Windows, Anaconda, Ubuntu, Jupyter Notebook, Docker, Amazon Web Services (AWS)
Storage
MySQL
Other
Clustering, Regression, Data Science, Data Visualization, Data Mining, Machine Learning, Data Analysis, Data Analytics, Deep Learning, Artificial Intelligence (AI), Convolutional Neural Networks (CNNs), Image Processing, Recommendation Systems, Natural Language Processing (NLP), Computer Vision, Text Classification, Text Categorization, Generative Pre-trained Transformers (GPT), Optical Character Recognition (OCR), Tesseract, Recurrent Neural Networks (RNNs)
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring