Skip to content
View Fshahnaj's full-sized avatar
1 follower · 1 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report Fshahnaj

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fshahnaj/README.md

👋 Hi, I'm Fujaila Shahnaj

Data/Analytics Engineer • Data Analyst • BI Developer • ML Engineer (Healthcare & Product Analytics)

🎓 MS Computer Science @ Clemson University (GPA 3.87)
📍 Raleigh–Durham–Cary–RTP (NC)
💡 Specializing in Healthcare Analytics, ML Pipelines, BI Systems & Data Engineering

🌟 About Me

I’m a data/analytics engineering professional with experience building end-to-end clinical analytics platforms, enterprise-grade Power BI dashboards, and NLP-driven product insights systems. I thrive in turning messy real-world datasets into clean, validated, explainable insights that guide business decisions.

  • Built ML + NLP pipelines analyzing 368K+ records
  • Developed a clinical risk prediction model (ROC-AUC: 0.79)
  • Designed BI dashboards for senior leadership (KPI, RLS, automated refresh)
  • Implemented dbt + DuckDB star-schema warehouses for healthcare datasets
  • Fine-tuned BERT & RoBERTa models (F1: 0.84)
  • Built ML pipelines analyzing 368K+ records
  • Designed clinical risk prediction model (ROC-AUC: 0.79)
  • Delivered Power BI dashboards for senior leadership decision-making
  • dbt + DuckDB star-schema modeling for healthcare data
  • NLP modeling with BERT & RoBERTa (F1: 0.84)

📊 Featured Projects

🔹 CardioInsight-AI — Healthcare Analytics Platform

End-to-end cardiovascular risk analytics system
— HIPAA-style de-ID → dbt warehouse → ML → Power BI clinical dashboard
ROC-AUC: 0.79

📈 Live Power BI Dashboard • 📂 GithubLink

🔹 Product Hunt Community Insights (368K+ records)

NLP pipeline using BERT/RoBERTa to classify user complaints, praise, and feature requests
F1 Score: 0.84 📘 Coming Soon

🛠️ Technical Skills

🔧 Languages

Python, SQL

📊 Data Analytics

EDA, KPI Development, A/B Testing, Statistical Analysis, Visualization

🧠 Machine Learning

Logistic Regression, Tree Models, BERT/RoBERTa, Feature Engineering, Model Evaluation

🏗️ Data Engineering

dbt (models, tests, documentation), ETL/ELT, Dimensional Modeling
DuckDB, MySQL, Oracle, Spark

📈 BI & Visualization

Power BI (DAX, M, Star Schema, RLS), Tableau, Matplotlib, Seaborn

☁️ Cloud

AWS (S3, Glue, Redshift), EC2, IAM

💼 Experience

Research Assistant — HAIE Lab | Clemson University
• Analyzed 368K+ Product Hunt comments using ML/NLP
• Built automated data pipelines (reduced processing time 60%)
• Developed BERT multi-label classifier (F1: 0.84)


Graduate Assistant — Data Analytics | Clemson Graduate School
• Designed enterprise Power BI dashboards
• Implemented RLS and automated refresh schedules
• Supported VPs/Deans with KPI tracking


Data Science Intern — Data Visualization Lab, Clemson Library
• Built forecasting models (85% accuracy)
• Created operational dashboards (Tableau/Power BI)
• ETL across 50K+ records


Senior Lecturer — PCIU (Study Leave)
• Taught DBMS, DS, Algorithms
• Supervised ML/AI research projects

📬 Contact

📧 Email: shahnajfujaila@gmail.com
🔗 LinkedIn: linkedin.com/Fujaila-Shahnaj
🌐 Portfolio: https://fshahnaj.github.io

⭐ Thanks for visiting! ⭐

Pinned Loading

  1. CardioInsight-AI CardioInsight-AI Public

    Production-grade ETL pipeline for cardiovascular risk analytics with HIPAA-compliant data processing, automated quality validation, and enterprise BI dashboards.

    Jupyter Notebook

  2. data-engineer-handbook data-engineer-handbook Public

    Forked from DataExpert-io-Community/data-engineer-handbook

    This is a repo with links to everything you'd ever want to learn about data engineering

    Jupyter Notebook

  3. Deep-Learning-Projects Deep-Learning-Projects Public

    Jupyter Notebook

  4. fork-commit-merge fork-commit-merge Public

    Forked from fork-commit-merge/fork-commit-merge

    Fork, Commit, Merge. A project designed to help you familiarize yourself with the open source contribution workflow on GitHub!

    JavaScript

  5. SoftwareFoundations SoftwareFoundations Public

    Forked from abastola0/SoftwareFoundations

    JavaScript

  6. FShahnaj.github.io FShahnaj.github.io Public

    HTML