Close

Khanh Duong TRAN

Data Scientist

Download Resume

About Me

An M.S.c Data Science & Analytics student, I am actively seeking internship opportunities.



Results-driven, business-oriented individual with Python proficiency for leveraging data to drive insights and decision-making. Multilingual in English and French, I bring an open-minded approach and always willing to embrace new challenges. My ability to adapt swiftly to new environments and my dedication to continuous improvement make me a valuable addition to any team.

Experience

Viettel Group

Asociate Data Analyst

  • Utilised SQL for the analysis of telecommunications customer usage data.
  • Assisted the synthesis of reports evaluating the effectiveness of Data Science applications compared to traditional telecommunication campaigns.
  • Researched tree-based Machine Learning algorithms for customer churn predictions.

    • NAPAS

    Cyber Security Intern

  • Collected 1,852 Threat Intelligence data entries through OSINT from the World Wide Web.
  • Filtered company's Threat Intelligence data in text format.
  • Prepared, finalized thesis in latex format via Overleaf.
  • Analyzed data for actionable insights in Cyber Security scenario.

    • Education

    EPITA - School of Engineering and Computer Science

    2023 - Present

    Masters of Science in Computer Science - Data Science & Analytics specialized

  • Completed an intensive curriculum that covered a broad range of topics within Data Science, including ML (Machine Learning), Relational Database, Mathematics, etc.
  • Engaged in collaborative projects with multidisciplinary teams, fostering effective cross-cultural communication and teamwork skills.
  • Developed advanced data analysis with Jupyter Python, extracting valuable insights from complex datasets.
  • Acquired proficiency in deploying ML models to production using FastAPI, integrated with PostgresSQL database.

    • University of Science and Technology of Hanoi

    August, 2018 - February, 2022

    Bachelor of Science in Cyber Security

  • Graduated with distinction degree.
  • Top 1% in the Cyber security specialization.
  • Awarded scholarship based on academic success.
  • Awarded certification for school activities contribution.

    • Projects

    News summarizer web app

    Explore NLP concepts by either building or fine-tuning pre-trained models for text summarization. The objective is to deploy these models onto a web application capable of summarizing news articles scraped from websites. The summarized content will be stored in a database for future refinement of models or monitoring of data drift issues. This project is in its conceptual phase, with implementation yet to begin.

    View Project

    Kaggle Playground series competitions

    Developed a machine learning model to achieve the best performance on a test set according to the competition's specific evaluation metric. The model's score was compared to others on a leaderboard to identify the most effective approach. Tools used include Python, Scikit-learn, Pandas, NumPy, Polars, OpenFE, and Optuna.

    View Project

    Telecommunications Churn prediction Analytics Platform

    Developed an MVP for predicting customer churn in telecommunications using advanced deep learning models. Utilized Python, TensorFlow, FastAPI, Streamlit, Grafana, Apache Airflow, Docker, and MLflow. The web application featured an interactive dashboard with insights on customer behavior, automated data ingestion, prediction processes, an email recommendation system for retention, and a feedback form for continuous model improvement.

    View Project

    Banking customers Churn prediction

    Built a machine learning model to predict which bank customers are likely to leave the service. Conducted exploratory data analysis with visualizations to understand data distribution, relationships, and imbalances to determine the appropriate models for the task. Tested different models, with a voting classifier ensemble performing best, evaluated using the F1 score. Tools used include Python, Scikit-learn, Pandas, NumPy, and Matplotlib.

    View Project

    Skills

    Get in Touch