Arsine S.

Data Scientist

Arsine is a talented Data Scientist with four years of experience specializing in Machine Learning, Business Analytics, NLP, and causal analysis.

She has worked as a Senior Data Scientist at Metric, where she developed state-of-the-art NLP approaches for product classification, information extraction, and prompt engineering.

Arsine has successfully completed various projects across different domains, including news analysis, product class identification, question-answering systems, human activity classification, house price prediction, and the development of a tax fraud detection framework.

Hauptkompetenz
  • Data Science 4 Jahre
  • Python
    Python 4 Jahre
  • Data Analytics 4 Jahre
Andere Fähigkeiten
  • Git
    Git 3 Jahre
  • SQL
    SQL 2 Jahre
  • Topic Modelling 2 Jahre
Arsine
Arsine S.

Armenia

Erste Schritte

Ausgewählte Erfahrung

Beschäftigung

  • Adjunct Lecturer

    American University of Armenia - 1 jahr 8 monate

    • Developed a graduate course on advanced data analysis topics, covering customer segmentation, PCA, research techniques, association rule mining, SQL basics, and more.
    • Adapted real-life company consulting projects for student assignments to apply learned concepts.
    • Designed a unique learning curriculum to fill knowledge gaps in data science and support future professional development.

    Technologien:

    • Technologien:
    • Data Science
    • Python Python
    • Data Analytics
    • Machine Learning Machine Learning
    • Data Engineering
    • PCA
    • Regression testing
    • Clustering
    • NumPy NumPy
    • Pandas Pandas
    • Plotly Plotly
    • Scikit-learn Scikit-learn
  • Senior Data Scientist

    Metric - 3 jahre 1 monat

    • Created an end-to-end pipeline for historical and real-time news scraping.
    • Implemented text cleaning, part-of-speech tagging, feature generation, and sentiment score evaluation.
    • Developed news text preprocessing and analysis to classify whether it was a rumor, based on a unique threshold scheme and forward-looking algorithm.

    Technologien:

    • Technologien:
    • Data Science
    • Python Python
    • Data Analytics
    • Machine Learning Machine Learning
    • Data Engineering
    • Data Modeling
    • NLP
    • Regression testing
    • Clustering
    • NumPy NumPy
    • Pandas Pandas
    • Plotly Plotly
    • Scikit-learn Scikit-learn
    • SciPy SciPy
  • Senior Data Scientist

    Metric - 4 jahre

    • Managed and led 360-degree US retail market research for data acquisition, cleaning, and early trend identification.
    • Performed extensive data quality checks for 10+ data sources and identified the most informative ones for environmental, demographic, and speed information.
    • Led data acquisition and scraping, merged various data sets, and created a fully automated working pipeline for continuous data updates and warehousing.
    • Conducted research to generate features and develop approaches for early identification of trends and the most promising locations.

    Technologien:

    • Technologien:
    • Data Science
    • Python Python
    • Data Analytics
    • Machine Learning Machine Learning
    • Data Engineering
    • Data Modeling
    • XGBoost XGBoost
    • Topic Modelling
    • ETL ETL
    • NumPy NumPy
    • Pandas Pandas
    • Plotly Plotly
    • Scikit-learn Scikit-learn
    • SciPy SciPy

Ausbildung

  • Dr. Phil.Economics

    Armenian State University of Economics · 2021 - 2026

  • MSc.Advanced Analytics and Machine Learning Track

    American University of Armenia · 2018 - 2020

  • BSc.Business

    American University of Armenia · 2014 - 2018

Portfolio

  • porfolio-0

Finden Sie Ihren nächsten Entwickler innerhalb von Tagen, nicht Monaten

In einem kurzen 25-minütigen Gespräch würden wir gerne:

  • Auf Ihren Bedarf bezüglich des Recruitments von Software-Entwicklern eingehen
  • Unseren Prozess vorstellen und somit wie wir Sie mit talentierten und geprüften Kandidaten aus unserem Netzwerk zusammenbringen können
  • Die nächsten Schritte besprechen, um den richtigen Kandidaten zu finden - oft in weniger als einer Woche

Unterhalten wir uns