Giang Portfolio Page

Biography

Standing at the exploration of big data and intelligence, I've been always curious about how we can solve real-world challenges in smarter, more efficient ways. This question led me to explore and adapt cutting-edge tools in cloud computing and data science.

With a Master of Science in Business Analytics and an AWS Solution Architect Associate certification, making an impact on the real world through valuable data-driven projects is my primary motivation to become a successful Data Analyst - Data Scientist in the future.

Education

Master of Science, Business Analytics

California State Polytechnic University, Pomona

Specializing in Data Science, Data Analytics, and Social Media Mining, applying advanced techniques to discover and solve challenging real-world problems.

Bachelor of Art, Hospitality Management

Duy Tan University

Specializing in Customer Assumption Analytics in the hospitality industry, with an undergraduate thesis utilizing regression modeling and IBM SPSS to analyze factors influencing hotel services and customer behavior in a local five-star hotel.

AWS Image — Certified Solution Architech

Professional Experience

Data Engineer

ScaleCapacity, California

January 2024 - July 2024

Debugged scripts to correct data formatting for the user-friendly appication, achieving a 90% reduction in errors.
Effectively developed and maintained ETL pipelines to transform and preprocess the large unpivoted datasets into normalized formats, enabling trend analysis and model building readiness.
Collaborated with senior developers to design AWS infrastructure and implement new feartures and enhancements.
Supported UI/UX team to provide valuable insights to optimize UI functionality and enhance user-friendly.
Worked with cross-functional teams to deliver end-to-end data solutions on time, achieving up to 90% of task completion on Jira board.

Data Scientist Intern

Boeing, California

January 2023 - August 2023

Led a team of three to develop Large Language Model for detecting aircraft corrosion in a complex dataset of 20,000 free-form text records from aircraft maintenance.
Analyzed unstructured data to optimize cost structures and reduce operational expenses, contributing to a 25% improvement in cost efficiency for aircraft maintenance.
Trained and validated a BERT model to detect misspellings and classify the primary entities in primary categories, achieving 92.6% accuracy.
Conducted statistical modeling to predict equipment failures, leading to 25% decrease in unexpected downtime.
Deveoped and presented Tableau visualization to managers for decision-making process, improving the understanding of financial impacts on operations and decision-making process.

Business Data Analyst

American Home 4 Rent

December 2022 - August 2023

Conducted a thesis project using a Recurrent Neural Network (RNN) to predict property damage from sequential patterns in a large historical dataset.
Designed a robust data pipeline to gather, transform, and preprocess over 150,000 property records and 2.3 million maintenance records spanning six years.
Actively worked closely with cross-department teams to identify the roots cause and key business drivers.
Created the normalized metrics to identify the trends analysis and relationship between property with budget, ages and geography insights.
Designed Tableau dashboard and presented trends analysis and the cost optimization model, contributing to decision-making among department managers and Vice President.

Skills

Programming Languages

3+ years experience with Python, R Statistic, Sequel Query Languag(SQL), SPSS.

Data Visualization

Tableau| Power BI| AWS Quick Sight| Python libraries: Plotly, Matplotlib, and Seaborn.

Machine Learning/AI

Hi, I'm Giang Nguyen