Data Science · Machine Learning · Analytics

Nguyễn Thị
Hiến Trang

Results-driven Data Science enthusiast transforming raw data into actionable insights through statistical analysis, predictive modeling, and data visualization.

View Projects Get in Touch
3+
ML Projects
87%
Best F1-Score
3.2
GPA / 4.0
Profile
Python
ML
SQL

About Me

Passionate about
data-driven solutions

Results-driven Data Science enthusiast with a strong foundation in Python, SQL, and Machine Learning. Proven ability to transform raw data into actionable insights through statistical analysis, predictive modeling, and data visualization.

Passionate about solving real-world problems through data-driven decision-making. Currently pursuing a Bachelor of Science in Mathematics and Computer Science at VNU University of Science, with a GPA of 3.2/4.0.

Thanh Xuân, Hà Nội
htrang130505@gmail.com
0869741305
GitHub Profile

Skills & Expertise

Core Competencies

Data Science & Analytics

Data Science Predictive Modeling Machine Learning Statistical Analysis Feature Engineering PCA / LDA A/B Testing Product Analytics

Technical Stack

Python SQL Pandas NumPy Scikit-learn PyTorch TensorFlow Web Scraping ETL Matplotlib Seaborn

ML Techniques

K-Means DBSCAN KNN XGBoost Collaborative Filtering Neural Networks Cohort Analysis Funnel Analytics

Soft Skills

Cross-functional Collaboration Business Translation Data Storytelling Dashboard Development Problem-Solving

Featured Work

Professional Projects

Mar 2026 – May 2026

Student Mental Health Burnout Analysis & Predictive Modeling

Built ML models to predict student burnout with 87%+ accuracy; identified 4 key stress factors affecting 65% of student population.

Python Pandas Scikit-learn NumPy Matplotlib Seaborn
Engineered 200+ features from raw survey data; handled 40% missing values using advanced imputation
Implemented PCA/LDA → reduced feature space by 85% while retaining 95% variance
Deployed clustering (K-Means, DBSCAN) → segmented into 4 burnout severity tiers
XGBoost achieved 87% F1-score, outperforming baseline by 18%
Code Demo
Jan 2026 – Feb 2026

Spotify Music Recommendation System & User Retention Analytics

Developed hybrid recommendation engine serving 500K+ simulated users; reduced user churn by 2.5x through skip-behavior segmentation.

Python TensorFlow Scikit-learn Matrix Factorization Pandas
Engineered hybrid recommendation system: Collaborative Filtering + Neural Networks
Users with skip rate >40% in first 3 days = 2.5× churn probability
Conducted funnel analytics: identified conversion bottleneck at day 2
Built interactive Jupyter dashboards for stakeholder review
Code Demo
Oct 2025 – Nov 2025

NYC Public Bus Data Analytics & Route Optimization

Identified 8 congestion hotspots; recommended 3 route optimizations estimated to save $200K annually in operational costs.

Python TensorFlow Plotly Google Maps API Pandas
Aggregated GPS data from 500+ buses across 50 routes; cleaned 15,000+ records
Built predictive delay model (Random Forest): RMSE = 4.2 minutes
Developed executive dashboards with delay heatmaps & demand forecasting
Presented findings to NYC MTA; recommendations under pilot review
Code Demo

Academic Background

Education & Certifications

Education

Sep 2023 – Present

VNU University of Science

Hanoi, Vietnam

Bachelor of Science in Mathematics and Computer Science

GPA: 3.2 / 4.0

Relevant Coursework

Calculus Probability & Statistics Linear Algebra Data Structures Algorithms

Certifications

Deep Learning Specialization

Coursera, Andrew Ng · In Progress

SQL for Data Analysis

DataCamp · Completed

Python for Data Science

Udacity Nanodegree · Completed

Activities

DataFlow 2024

Organizing Committee Member

HAMIC

HUS Applied Mathematics and Informatic Club · Active Member

Get In Touch

Let's Connect

I'm always open to discussing data science, machine learning projects, or potential opportunities.

Email

htrang130505@gmail.com

GitHub

View my projects

Phone

0869741305
Vietnamese (Native)
English (Fluent)
Hà Nội, Vietnam