top of page
Hello! My name is
MIN CHANG
I am a BI Engineer and Data Analyst, currently pursuing my Master’s in Data Science Engineering at Northeastern University. Most recently, I worked as a Business Intelligence Engineer Intern at Amazon, where I built SQL pipelines, automated reporting workflows, and developed interactive dashboards in QuickSight to support large-scale supply chain execution.
00:00 / 02:36
Recruiting can be stressful. Here’s some jazz to ease the scroll.
Get to Know Me
My background spans Marketing Analytics, Business Intelligence, and Data Engineering fundamentals, giving me the versatility to move seamlessly between data analysis, pipeline design, and visualization. I have strong experience with Python, SQL, ETL automation, and statistical modeling, and I’m passionate about applying these skills to uncover actionable insights and build scalable data solutions.
Driven by curiosity and a deep interest in machine learning and predictive analytics, my long-term goal is to grow into a Data Scientist role where I can apply advanced models to solve complex, real-world problems.
"No one can whistle a symphony. It takes a whole orchestra to play it"
- H.E. Luccock
My Latest Projects
NLP/Sentiment Analysis on IMDB Reviews
This project focuses on sentiment analysis using the IMDB movie review dataset, which contains 50,000 labeled reviews. Our goal was to compare different machine learning and deep learning approaches — including Naive Bayes, LSTM, and BERT — to see how well each model could classify reviews as positive or negative. By evaluating their F1 scores and error patterns, we identified the strengths and weaknesses of each method for sentiment classification.
Smart Contract Vulnerability Risk Analysis
• Conducted unsupervised machine learning & K-means for hierarchical clustering analysis in Python using Euclidean and Jaccard Distance metrics on binary datasets of compiled risk tags, leveraging these metrics for their precision in quantifying similarity in binary data structures
• Created and analyzed heatmaps, dendrograms, and histograms, to visualize and quantify complex relationships and shared security vulnerabilities in smart contracts, which supported strategic risk management decisions.
• Validated peers' data labels to ensure accuracy and reliability of data sets.
• Performed frequency & correlation analysis of risk tags using Python to identify the most prevalent vulnerabilities and their associations, gaining proficiency in data manipulation and statistical tools.
• Created and analyzed heatmaps, dendrograms, and histograms, to visualize and quantify complex relationships and shared security vulnerabilities in smart contracts, which supported strategic risk management decisions.
• Validated peers' data labels to ensure accuracy and reliability of data sets.
• Performed frequency & correlation analysis of risk tags using Python to identify the most prevalent vulnerabilities and their associations, gaining proficiency in data manipulation and statistical tools.
Predicting Potential Diabetic Female Patients with Diagnostic Measurements
This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases. The objective is to predict based on diagnostic measurements whether a patient has diabetes. In this project, I developed Classification and KNN models to predict whether a female patient has diabetes.
Building a Calculator with Java Object-Oriented Programming
In this project, I developed a basic yet functional calculator using Java. The objective was to create an intuitive user interface alongside robust back-end logic that could handle fundamental arithmetic operations such as addition, subtraction, multiplication, and division.
Project: Hyundai QBR 2023
In the Q3-Q4 review for 2023, I led a critical analysis project at Hyundai, tasked with organizing and reviewing multiple complex datasets from October to December. The primary challenge was to assess the applicability and organization of extensive data to ensure its relevance and accuracy for the project’s goals. I developed and executed numerous complex SQL queries for data joining, migration, aggregation, parsing, and cleaning. Leveraging Alteryx cloud technologies, I automated and scheduled data workflows, which significantly enhanced operational efficiency. I created detailed Tableau visualizations to present key insights and KPIs to upper management effectively. As the project lead, I collaborated closely with analysts, Quality Assurance, and Engineers, ensuring the integrity and utility of data in driving strategic decision-making
Anomaly Detection - Under-fitting
As a Data Scientist at Hyundai, I undertook a project aimed at developing a robust model to accurately detect anomalies in warranty claims. The primary goal was to identify unusual patterns that might indicate fraud or systematic issues, ensuring the integrity and efficiency of the warranty claims process.
Predicting Warranty Claim Validity with Bias-Variance Tradeoff
One of the projects at Hyundai was to develop a ML model to predict the validity of warranty claims based on historical data. The team needed a model that could quickly identify and process valid claims and reduce the time and resources spent on investigating fraudulent or incorrect claims.
Neural Network Modeling using Python TensorFlow
In this project, I forecasted Hyundai's parts freight and supply chain costs by creating a simple recurrent neural network (RNN) for its effectiveness in handling sequential data. I developed a basic model using Python TensorFlow's Keras API to predict future costs based on the WTC historical data, consisting of monthly freight and supply chain costs.
Advanced SQL Querying Techiques with Big Data
During my tenure at Hyundai, I focused on Advanced SQL querying for Big Data, leveraging techniques such as Recursive CTEs, Date-Time Manipulation, Delta Values, and parsing. This initiative allowed me to develop complex SQL queries that optimized data analysis and reporting processes
Google Data Analytics Capstone Project
Utilized R and SQL to analyze anonymized FitBit data, aiming to understand user engagement and identify trends for Bellabeat's marketing strategies. The focus was on deriving actionable insights from datasets concerning daily activity, sleep patterns, and fitness goals.
Alteryx ETL Pipelines with Hyundai Big Data
During my tenure at Hyundai, I developed over 30 ETL automations using Alteryx and SQL, significantly enhancing data processing workflows for projects. This initiative not only streamlined the integration and cleansing of data but also deepened my expertise in managing complex data structures and optimizing data storage solutions. Details are kept confidential due to privacy and security considerations.
Osteoporosis Risk Analysis with Machine Learning
The dataset provides lifestyle details of individuals with and without osteoporosis, including demographic information, lifestyle factors like physical activity, smoking, and alcohol consumption, and medical history. It aims to aid research in osteoporosis risk prediction and analysis, enabling the development and evaluation of machine learning models to identify individuals at risk based on various health factors.
Relational Database Design and Management
This project involved designing comprehensive relational models and creating optimized and scalable database architectures, implementing efficient data relationships, and managing database operations to support data transactions and complex queries.
Quantitative Analysis with SQL
The organization I was employed with required a comprehensive analytical report, one that necessitated the integration of voluminous datasets aggregated from numerous relational database systems. My responsibility encompassed devising a sophisticated query to extract pertinent insights, which were to be disseminated to our stakeholders
Data Visualization with Tableau
In this series of projects, I leveraged Tableau to create intuitive and interactive data visualizations for a variety of datasets, including Airbnb listings, Superstore sales, Tesla stock prices, sales KPIs, and customer aggregation. These visualizations aimed to enhance decision-making processes by providing clear insights into trends, patterns, and outliers within the data.
PySpark with Apache Spark
Set up a server-less Apache Spark session with Jupyter, aiming to streamline the process of big data processing without the overhead of managing server infrastructure. The goal was to create an accessible and scalable data analysis environment that could efficiently handle large datasets.
Algorithm Implementation and Analysis Using Python
This project involved implementing and analyzing algorithms using Python, focusing on asymptotic analysis, quicksort, probability calculations, and linear time selection. The primary objective was to develop efficient algorithms for sorting and selection, and to assess their performance and probabilistic characteristics in various scenarios.
Statistical Process Control, Supply Chain, & Project Management
I implemented Statistical Process Control, optimized Supply Chain operations, and enhanced Project Management practices in a multifaceted initiative. This involved applying advanced statistical techniques to monitor production quality, streamlining logistics to boost efficiency, and deploying robust project management strategies to ensure timely delivery of projects.
Customer Churn Prediction with R Programming
Delgado Protocol has been experiencing higher than average customer churn rates, which impacts revenue and increases the cost associated with acquiring new customers. The existing models do not adequately address the complexities of customer behaviors and interactions with Delgado's services, partly due to incomplete data and lack of robust predictive analytics.
IBM SPSS Research for CSUF Student & Faculty Survey
Working with a group, we designed and administered a comprehensive questionnaire targeting the CSUF community. Utilizing IBM SPSS Statistics, our group conducted a detailed exploratory analysis of the collected data. We employed a range of statistical techniques including Chi-Square Tests, Variance Analysis, ANOVA, Frequency Analysis, Multi-Response Frequency, and Crosstabs. This rigorous analytical approach enabled us to uncover significant insights and patterns that were crucial for understanding the dynamics within the student and faculty populations at CSUF.
Data Visualization with Microsoft Power BI
Data visualizations focusing on Impression Analysis and Web Traffic by Geography. By integrating diverse datasets, I crafted interactive dashboards that provided a comprehensive view of user impressions and web activity across different regions.
SAP ERP Analytics Simulation
The SAP Hana ERP Analytics Simulation allowed me to gain hands-on experience with real-world business scenarios. Through this simulation, I learned to navigate the complexities of SAP's data environment, extracting and analyzing data to make informed business decisions. This experience sharpened my analytical skills, deepened my understanding of enterprise resource planning systems
Forecasting Moving Average & Exponential Smoothing
In this project, I applied Moving Average and Exponential Smoothing techniques to forecast U.S. gasoline sales. By analyzing historical data, I was able to effectively model trends and seasonal fluctuations. The Moving Average method smoothed out short-term variances, while Exponential Smoothing dynamically adjusted to changes.
MySQL Database Administration with Phpmyadmin
Administered a MySQL database using phpMyAdmin, focusing on optimizing and maintaining the system for efficient data management. I set up and configured databases, executed complex SQL queries. Additionally, I performed regular backups and monitored database performance to ensure robust functionality
Google Data Analytics Specialization Certified
Issued on July 2022
ID Credentials: AEJDB6WEVLU5
Prepare
Ensuring ethical data analysis practices, addressing issues of bias and credibility, accessing databases and importing data, writing simple queries, organizing data.
Process
Connecting business objectives to data analysis, cleaning small and large datasets using Excel Spreadsheets, SQL, R, Python, documenting data-cleaning processes
Analyze
Converting, formatting, sorting, and filtering data using SQL queries, substantiating data analysis processes, understanding the purpose of different business communication tools,
Visualize
Creating visualizations and dashboards and filters in Tableau, telling a data-driven story, creating static infographics and interactive tools that can be consumed online or in print.
bottom of page