Henry Chang

Data and Analytics Internship

Zurich Insurance Group•  May 2024 - August 2024•  Schaumburg, IL

Built a Power BI report to visualize and map relationships between datasets and Power BI tables by leveraging metadata queried through DAX Studio. Developed a Power BI application integrating Power Apps and Power Automate for data write-back to SQL databases and tasks initiation via API calls. Designed a Python script to fetch and parse data from an API, then containerizing using Docker. Aided in testing a generative AI document summarization model on medical records. Collaborated on redesigning a data ingestion and curation process, utilizing Scala and PySpark to establish external tables within Databricks, orchestrated through Azure Data Factory.

Undergraduate Research Assistant

Purdue University – Lee Memory and Cognition Lab•  January 2024 - April 2024•  West Lafayette, IN

Utilized 'all-mpnet-base-v2' for text embeddings, analyzed semantic similarities with cosine similarity, and visualized the data topics via PCA and K-Means clustering. Developed a custom machine learning model using Python and TensorFlow to detect the mouse cursor's location within images extracted from videos using OpenCV.

Undergraduate Research Assistant

Nationwide Insurance•  January 2024 - April 2024•  West Lafayette, IN

Partnered with Nationwide Insurance through the Purdue Data Mine and Contributed to developing the Pricing Impact Estimator (PIE), a suite of predictive statistical models focusing on various car insurance types, by utilizing Python for extensive data processing and transformation. Studied logistic generalized linear models as part of the project's research methodology.

Information Services Internship

Northwestern Medicine - Healthcare•  May 2023 - December 2023•  Chicago, IL

Facilitated data management by collaborating with the Messaging and Active Directory team, utilizing PowerShell scripting, and implementing multiple automation through Azure Runbooks. Built a digital solution through Microsoft Azure. Leveraged and cleaned device data to train a machine-learning model using Python, Databricks, and AutoML. Developed and presented a Power BI dashboard. Developed a Power App by seamlessly integrating PowerShell scripts through Azure DevOps.

Purdue University, College of Science

Data Science, BS•  August 2022 - Present•  GPA: 3.6

Purdue University, College of Science Bachelor of Science, Data Science and Artificial Intelligence Honors Student, Dean’s List and Semester Honors West Lafayette, IN Aug 2022 – Dec 2025 GPA 3.6/4.0 • Coursework: Data Mining and Machine Learning, Introduction to Artificial Intelligence, Introduction to Data Science, Introduction to Information Systems, Computational and Object Orientated Programming, Data Engineering in Python, Data Structures and Algorithms, Statistical Theory, Statistics for Data Science in R, Probability, Linear Algebra, Multivariate Calculus, Ethics for Engineering, Economics.