Andrea C.

Senior Data Scientist

Andrea is a Data Scientist with ten years of experience in both academia and industry, blending scientific rigor with practical business solutions.

He specializes in optimization, forecasting, and building data pipelines, with hands-on experience developing AI-driven systems for logistics, retail, and HR platforms.

At PVH Europe, Andrea delivered €3M in annual savings by developing a linear programming solution and led a warehouse optimization project using genetic algorithms. He is highly skilled in Python, SQL, PySpark, Airflow, and AWS.

Known for his attention to detail and collaborative approach, Andrea excels in cross-functional teams and consistently transforms complex challenges into scalable, high-impact data products.

Main expertise

  • Python
    Python 10 years
  • Data Science 5 years
  • Git
    Git 10 years

Other skills

  • AWS Athena
    AWS Athena 2 years
  • XGBoost
    XGBoost 2 years
  • PostgreSQL
    PostgreSQL 2 years
Andrea

Andrea C.

Netherlands

Get started

Selected experience

Employment

  • Data Scientist

    PVH Europe - 3 years 2 months

    PVH Europe is a multinational apparel company behind iconic brands like Tommy Hilfiger and Calvin Klein. Andrea was an early Data Science & Analytics team member, supporting logistics and supply chain operations with AI and optimization solutions.

    • Designed and implemented a linear programming model to improve stock-to-order fulfillment, yielding estimated annual savings of €3M.
    • Led a major initiative on warehouse slotting optimization using a genetic algorithms-based approach.
    • Built robust data pipelines with PySpark and Airflow to automate and streamline reporting for various business stakeholders.
    • Trained forecasting models to predict retail store foot traffic using LSTM-based recurrent neural networks.
    • Trained a Random Forest model to forecast inbound logistics volume and implemented automated retraining workflows.
    • Maintained CI/CD infrastructure and Docker environments for the data science team, ensuring reliable cloud job execution on AWS.
    • Acted as a lead code reviewer, overseeing coding quality and maintaining the team’s internal Python package (dscin_ppy).

    Technologies:

    • Technologies:
    • Docker Docker
    • AWS AWS
    • Python Python
    • SQL SQL
    • AWS S3 AWS S3
    • Bash Bash
    • Data Science
    • NumPy NumPy
    • Keras Keras
    • Pandas Pandas
    • AWS Athena AWS Athena
    • Git Git
    • VSCode VSCode
    • SciPy SciPy
    • Scikit-learn Scikit-learn
    • ELT
    • Apache Airflow Apache Airflow
    • Matplotlib Matplotlib
    • ETL ETL
    • Machine Learning Machine Learning
    • Asana Asana
    • Problem solving
    • SAP SAP
    • Process Optimization
    • Supply Chain
    • PySpark PySpark
    • SAP S/4HANA SAP S/4HANA
    • Seaborn Seaborn
  • Data Scientist

    Listopro - 1 year 11 months

    Listopro is a rapidly growing remote staffing platform that connects LATAM tech talent with U.S. and global employers. Andrea served as their first and only Data Scientist.

    • Improved the platform’s internal CRM search engine by implementing an XGBoost model, which reduced candidate identification time by 40%.
    • Created and maintained internal KPI dashboards using Streamlit, with interactive visuals powered by Plotly.
    • Developed a transformer-based NLP model to automatically classify job descriptions in candidate resumes.
    • Mined CRM system data to uncover and resolve irregularities, enhancing system reliability.
    • Contributed to backend development by extending Django functionalities and optimizing data storage to better support machine learning workflows and future scalability.

    Technologies:

    • Technologies:
    • PostgreSQL PostgreSQL
    • Django Django
    • Python Python
    • SQL SQL
    • Bash Bash
    • Data Science
    • Google Cloud Google Cloud
    • NumPy NumPy
    • XGBoost XGBoost
    • Pandas Pandas
    • Git Git
    • VSCode VSCode
    • Scikit-learn Scikit-learn
    • ELT
    • Matplotlib Matplotlib
    • NLP
    • Machine Learning Machine Learning
    • SQLAlchemy SQLAlchemy
    • Streamlit Streamlit
    • Plotly Plotly
    • Problem solving
    • Hugging Face Transformers Hugging Face Transformers
    • Seaborn Seaborn
    • DAX
  • Science 2 Data Science (fellow)

    Pivigo - 1 month

    Completed an intensive five weeks, Data Science training program for PhDs, focused on delivering a real-world big data solution with immediate business impact.

    • Delivered an NLP project in a team of five using Agile methodology, completing it from ideation to prototype.
    • Engineered a full text-analysis pipeline for cleaning, topic modeling, and clustering a corpus of human-written documents.
    • Applied deep learning methods, including a BERT-based model, to extract key topics and automate information retrieval.
    • Built a classification system to tag and categorize incoming documents, significantly reducing onboarding time for new business partners.

    Technologies:

    • Technologies:
    • Python Python
    • NumPy NumPy
    • Pandas Pandas
    • Agile Agile
    • Git Git
    • VSCode VSCode
    • SciPy SciPy
    • Scikit-learn Scikit-learn
    • Matplotlib Matplotlib
    • NLP
    • Machine Learning Machine Learning
    • Problem solving
    • Hugging Face Transformers Hugging Face Transformers
    • Hugging Face Hugging Face
  • Decision Intelligence Engineer

    White Space Energy - 3 months

    White Space Energy (now White Space Solutions) was a small consultancy company supporting decision-making in the Oil & Gas industry through data-driven and AI-based solutions. Andrea was an early recruit before the company rebranding.

    • Developed a backend forecasting algorithm using client-provided reservoir data.
    • Delivered a custom, flexible tool that predicted natural gas production under varying scenarios, enabling more informed operational planning.
    • Enhanced an existing Python algorithm by generalizing it to account for broader geological and operational conditions.
    • Collaborated closely with the project manager, software engineer, DevOps specialist, and the client’s technical team to ensure seamless deployment and integration.

    Technologies:

    • Technologies:
    • Python Python
    • Data Science
    • NumPy NumPy
    • Pandas Pandas
    • Git Git
    • VSCode VSCode
    • SciPy SciPy
    • Scikit-learn Scikit-learn
    • Matplotlib Matplotlib
    • Problem solving
    • DAX

Education

  • Doctor Of PhilosophyPhysics

    Stockholm University · 2014 - 2019

  • MSc.Physics

    University of Amsterdam · 2012 - 2014

  • BSc.Physics

    University of Trieste · 2007 - 2011

Find your next developer within days, not months

In a short 25-minute call, we would like to:

  • Understand your development needs
  • Explain our process to match you with qualified, vetted developers from our network
  • You are presented the right candidates 2 days in average after we talk

Not sure where to start? Let’s have a chat