cv

General Information

Full Name Linh P. Nguyen
Skills Python, SQL, R, Java, C, Dart, MVC, Microsoft Excel, Tableau, Algorithms and Data Structures, Machine Learning, Artificial Intelligence, Big Data, Statistical Data Analysis, Hypothesis Testing, Database Management Systems, Data Visualization, System Design, Linear Algebra, Web Development

Education

  • 2022.01-2024.09

    Philadelphia, PA
    B.S. in Data Science; minor in Computer Science
    Drexel University
    • GPA 4.0/4.0, Dean’s List
    • GHC 23 Scholar, Anthony J. Drexel Merit Scholarship, Day Alumni Fund
    • Teaching Assistant (20 hrs/week) for Data Science Programming (INFO 212) and Database Management Systems (INFO 210)
  • 2018.09-2021.06

    Birmingham, UK
    Bachelor of Pharmacy
    University of Birmingham
    • GPA 4.25/4.0, First-Class Honors
    • Finished 3 out of 4 years
    • International Scholarship Award (Highest Scholarship)

Experience

  • 2023.09-now

    Remote, PA
    Data Scientist Co-Op
    Oracle
  • 2023.06-2023.09

    Sunnyvale, CA
    Software Development Engineer Intern
    Amazon
    • Created a JIRA-enhancing tool to optimize task automation and workflow efficiency. The product is currently in use, contributing to improved efficiency in project management and communication within the organization. Utilized AWS DynamoDB for data transformation, harnessed AWS EventBridge, Lambda, and SES for automation. Employed Java for backend development, MVC with JSP for front end, and Coral Services for API integration.
    • Developed new functions for existing packages and seamlessly integrated them into Native AWS products using Java and AWS external/internal tools.
  • 2023.01-2023.03

    Remote, UT
    Data Scientist Intern
    Intermountain Health
    • Developed AI/ML recommendation system for clinical/supply chain staff for Doctor Preference Cards (DPC) decision-making process based on analysis of complex data sets of over 55,000 DPC using statistical functions, PySpark, and SQL, preventing a potential $13.65M yearly loss of surgical savings.
    • Provided executive-level, data-driven insights and visualizations that replace Tableau by implementing a more effective analytic application.
    • Designed baseline ML models to predict optimal supplies purchase for perioperative procedures, expected to result in savings of $7M/year by reducing surgical supply spending, optimizing working capital, and reducing inventory spoilage.
  • 2022.06-2023.09

    Philadelphia, PA
    Research Assistant
    Rezapour Lab Drexel University
    • Conducted data collection and analysis on social media to extract and investigate unstructured user-generated content, utilizing natural language processing ML models to classify characteristics of drug-related discussions for the baseline of an AI chatbot.
    • Conducted in-depth research and analysis on computational social science, focusing on evaluating moral values in texts, optimism/pessimism detection, and methods for maintaining a positive sentiment in online communities.
  • 2021.06-2021.12

    Hanoi, Vietnam
    Data Analyst Intern
    Vietnam Ministry of Health – Nanocovax Vaccine (Phase II and III)
  • 2020.06-2020.09

    Hanoi, Vietnam
    Intern
    Vinmec International Hospital
  • 2018.12-2021.12

    Birmingham, UK
    Math Tutor
    Tutorful
    • Delivered 3000+ hours of tailored mathematics instruction to multiple levels, including KS3, GCSE, A-Level, and other qualifications.

Leadership and Activities

  • 2023.11-now

    Philadelphia, PA
    Ambassador
    Women in Data Science (WiDS)
  • 2023.02-now

    Philadelphia, PA
    Founder
    Drexel Association for Data Science
    • Collaborated with fellow co-founders to establish the association’s vision, mission, and goals, and developed a strategic plan. Actively engaged in networking with professors, mentors, and business partners to establish meaningful relationships and foster collaborative opportunities for members.
  • 2022.09-now

    Philadelphia, PA
    Senior CCI Dean’s Ambassador
    Drexel University
    • Exemplified student leadership and community-building skills, representing Drexel University and advocating for the student body to various stakeholders (students, parents, partner schools, VIP guests, etc.). Developing valuable skills in public speaking, networking, marketing, and communications.
  • 2019-2021

    Birmingham, UK
    President
    Vietnamese Society of University of Birmingham
    • Coordinated with Honorary Presidents and officers of the Embassy of S.R. Vietnam and 100+ members from other universities to organize events and support 12000+ Vietnamese students in the U.K. Collaborated with several societies to organize 10+ cultural events annually.
  • 2019-2021

    Birmingham, UK
    Competitions Sub-committee and International Representative
    British Pharmaceutical Students’ Association
    • Coordinated with 1000+ members from the British Pharmaceutical Students’ Association, European Pharmaceutical Students’ Association, and International Pharmaceutical Students' Federation to help international students prepare and take license examinations.
    • Promoted international events and projects; monthly managed programs; prepared and promoted the annual international conferences.

Technical Projects

  • Fake News Detection Text-Processing and Natural Language Processing
    • Led a team of four to develop an efficient NLP model to predict the authenticity of 72,134 online news articles.
    • Performed text preprocessing such as removing noise, tokenization, lemmatization, performing TF-IDF, etc.
    • Examined seven Neural Network models (with Long Short-Term Memory) achieved the highest accuracy (94.51%) and F1 (94.71%) scores.
  • Brain Tumor Detection from MRI Images Image-processing and Deep Learning
    • Developed deep learning models for brain tumor detection using MRI images by employing MLP, CNN, VGG16, EfficientNet B2, and InceptionV3 models. Achieved the best performance using InceptionV3 with an F1 score of 93.55% and an accuracy score of 94.74%.
    • Performed pre-processing using data generators for image processing and augmentation with the ImageDataGenerator.
  • Credit Card Default Classification Data Mining and Machine Learning
    • Performed EDA to visualize/investigate the dataset, and built classification models using Scikit-learn, PyTorch, and Matplotlib.
    • Improved the F1 score of a simple Logistic Regression from 0% to 54.62% with an accuracy of 80.33% by tuning the decision threshold and other hyperparameters of the Extreme Gradient Boosting (XGBoost) model.
  • Salary Prediction Regression Prediction
    • Mined and cleaned data from over 1 million records using SparkML and SparkSQL following the ETL process and Label Encoding method.
    • Built and trained 5 regression machine learning models to predict the salary to find the best-predicted salary model based on backgrounds by comparing RMSE and R-squared scores. The model with the best scores has an R-squared of 74.88%.