Projects
A collection of practical case studies demonstrating my end-to-end data science capabilities. Each project leverages open-source data to showcase how I translate complex technical challenges into actionable insights.
​
*Due to confidentiality agreements, professional work cannot be publicly shared. Instead, the portfolio features personal projects that reflect the tools, techniques, and outcomes applied in professional and client-facing settings.
Focus Areas:​​​
Data
Modeling
Applying predictive modeling and clustering using machine learning techniques.
Big Data Implementation
Configuring and operating within modern Big Data environments.
​​​​
Data-to
-Insight
Skills spanning the full data lifecycle, from ETL to storytelling, reflected across the portfolio.
Tools & Techniques Featured in This Portfolio:
​
-
Core Data Science Methods: ETL, data engineering, querying, analytics, predictive modeling, machine learning, visualization
-
Business Intelligence & Visualization: Power BI, Tableau, ArcGIS
-
Programming & Query Languages: Python, SQL
-
Big Data Technologies: Google Cloud Platform (GCP), Hadoop, Spark, Hive
​
This is a living collection of my work, actively growing as I explore new techniques and challenges.
2025
-
Date: Dec 2025
-
Tool: Excel
-
Project Outcome: An analytics framework to support pricing and promotion decisions by integrating price elasticity and spending efficiency, enabling growth-oriented strategies while managing financial constraints.
-
Date: Sep 2025
-
Tools: Python, Visual Studio Code
-
Project Outcome: An evaluation of three clustering models to identify the optimal algorithm for mental health risk recognition.
-
Date: Aug 2025
-
Tools: Python, Visual Studio Code
-
Project Outcome: An evaluation of three classification models to identify the optimal algorithm for accurate PCOS diagnosis.
-
Date: Apr 2023
-
Tools: Power BI, RapidMiner
-
Project Outcome: Interactive Dashboard, Machine Learning model comparison
-
Date: Mar 2023
-
Tool: ArcGIS Online
-
Project Outcome: An ArcGIS StroyMap
-
Date: Feb 2023
-
Tools: Google Cloud Platform (GCP), HDFS, Spark ML
-
Project Outcome: Scalable ML deployment in a big data environment using Spark on GCP
-
Date: Jan 2023
-
Tool: Tableau
-
Project Outcome: A personalized dashboard to visualize and interpret health behaviors
2022
-
Date: Nov 2022
-
Tools: Google Cloud Platform (GCP), HDFS, Apache Hive
-
Project Outcome: An analytics report (for non-technical audience) and a script with Hive queries
