massiHUB
Data Analytics Portfolio
- LinkedIn profile
- What I am good at
- What I deliver
- What am I most proud of?
- Why hiring me?
-
Portfolio Projects
- Technical Skills
Portfolio Projects
Tennessee Integrated Traffic Analysis Dashboards
Tools: Tableau, SQL
Built 4 interactive dashboards replacing 100+ pages of monthly reports, driving operational insights for state traffic analysis:
Highlight: Fatal and Serious Injury Crashes
This dashboard comprises near-real-time interactive information on fatal and serious injury collisions on Tennessee roadways for the current and previous years.
The dashboard enables a nuanced analysis of fatal and serious crashes through interactive filters and graphs, powered by a SQL database and Tableau. Users can analyze trends and patterns by location, road conditions, time of day, victim demographics, and other parameters. The dashboard provides actionable insights to inform traffic safety policies, enforcement initiatives, infrastructure improvements, public education campaigns, and other countermeasures aimed at reducing crash-related deaths and injuries on Tennessee roads.
The dashboard was presented at the 2019 LifeSavers Conference, an annual conference on injury prevention and traffic safety organized by the National Safety Council. (Link)
- Designed KPIs and interactive reports for law enforcement and policy teams.
- Earned a Pay-for-Performance (P4P) award for operational efficiency.
Key Features:
- Dynamic filtering & drill-downs
- Multi-year traffic and incident trend analysis
Cancer Genomics Data QC Automation
Tools: Python, Linux, REST-API
Automated large-scale, unstructured genomic data quality control at the University of Chicago’s Center for Translational Data Science.
- Cut data QC processing time by ~50%.
- Developed reusable Python scripts for error detection, data migration, and cleaning.
- Supported users via help desk, script writing, and documentation.
Key Features:
- Automated QC pipelines
- API-based data retrieval & validation
- End-user support & documentation
Student Life Data Integration Dashboard
Tools: Python, Power BI, Semantic models
Developed an automated data pipeline integrating data from multiple university departments for operational insights. Designed dashboards to track student engagement, program outcomes, and operational KPIs.
- Automated data cleaning and integration process from disparate systems.
- Created interactive dashboards reducing reporting time for stakeholders.
- Increased data visibility across Student Life Effectiveness initiatives.
Key Features:
- Live data connections
- Multi-stakeholder reporting views
- Role-based access dashboards
Data Quality Testing in Agribusiness Software
Tools: Excel VBA
Performed QA analysis at EFC Systems Inc (Now Ever.Ag), identifying algorithmic inconsistencies across platforms.
- Designed test scenarios mimicking real-world use.
- Discovered critical discrepancies between iOS and Windows software versions.
Key Features:
- Automated data checks
- Cross-platform behavior validation
Research Data Analysis and Experimental Design Projects
Tools: Excel, VBA, SAS
Oversaw 9 research projects supervising statistical analysis and experimental design.
- Taught statistics and experimental methodology.
- Developed low-cost protocols to optimize student research budgets.
Key Features:
- Multivariate analysis
- Experimental designs
Publications: ORCID profile
Miscellaneous Projects:
Land Use Change in Tennessee - Nashville Software School
Tools: Python (SciKit), R (ShinyApp)
-
The objective of this project was to elucidate patterns and hypothetical rationales for land use changes in Tennessee. It comprised two sub-projects:
-
A slideshow reviewing the methodology and results is included with the phase II set of files.
-
The visualizations depicted various correlations between land availability and valuation across counties. Analyses suggested the predominant criteria influencing land value are proximity to major metropolitan areas and agricultural profitability.
-
In summary, this project leveraged statistical programming languages and multivariate analysis to glean scientific insights into drivers of land use trends. The interactive dashboards and dimension reduction models provide data-driven understanding of how exurban dynamics shape land use patterns over time. Further research could relate the identified factors to policies on zoning, land conservation, transportation infrastructure, and urban development.
Key Features:
- Principal Component Analysis
- k-Nearest Neighbors
Improve College-Going and College-Readiness - Division of Research and Evaluation, TN Dept of Education
Tools: Python
-
This repository comprises the data and computer code (in Python, in a Jupyter notebook) for an assessment project to identify measures that can evaluate high school graduates’ preparedness for collegiate studies.
-
Researchers have a great interest in enhancing college readiness for all youth and increasing the rate of postsecondary enrollment among graduates. The community is equally passionate about improving its students’ postsecondary success. For many of these students, college is not perceived as a viable option. Researchers posit that the district can improve college readiness among all district students by first identifying high schools to serve as “models of excellence” and then learning from these exemplars about best practices for producing “college-ready” students who enroll and persist in postsecondary education. Therefore, the available data was examined to recommend a model school.
-
Utilizing principal component analysis (aka dimension reduction), viable criteria were selected, upon which model schools were chosen. It appears that the most distinguishing factors to utilize for scoring are:
- The standardized grades (mathematics, SAT assessments)
- Enrolling for college. The two metrics that seem most relevant are: Enrolling for a 4-year degree (i.e., a strong education), and enrolling shortly after high school (an index of passion for education).
-
However, regarding data quality, there were both missing values and duplicated entries in the dataset. The strategy to manage the data was deliberated and implemented. Further research avenues (disaggregating the data within sub-regions) were suggested.
Key Features:
- Principal Component Analysis
Logistic Regression - Nashville Software School
Tools: Python
- This Jupyter notebook was developed to exhibit the concept of logistic regression, and how to implement this technique in Python. The code generates a logistic regression model, prints the model summary, exports and prints the coefficients, calculates predicted probabilities, and visualizes the logistic regression model along with the original data. The logistic regression model is applied to a binary response variable based on an explanatory variable. The visualization helps to understand how well the logistic regression model fits the data.
Technical Skills
Languages: Python, R, SQL, GraphQL, DAX, VBA
Tools: Power BI, Tableau, SAS
Techniques: Experimental designs, Multivariate & Regressional Analysis, A/B testing
What I am good at:
-
Data Storytelling & Insight Translation: I have a natural ability to translate raw, complex data into clear, actionable insights. Where others see spreadsheets and messy datasets, I instinctively see narratives and opportunities for improvement. This talent has made me the go-to person for dashboard development and reporting transformations.
-
Process Automation & Workflow Optimization: I’m consistently recognized for my knack for streamlining inefficient processes. Whether it’s automating data pipelines or reducing reporting time through code, I thrive on building solutions that save time and reduce human error.
-
Technical Versatility Across Domains: With hands-on experience in Python, R, SQL, SAS, Tableau, Power BI, and even REST APIs and GraphQL, I easily navigate between tools and platforms — a skill that makes cross-functional collaboration smoother and projects more resilient.
-
Mentorship & Cross-Functional Coordination: From mentoring students and analysts to liaising between data curators, owners, and stakeholders, I excel at relationship management. I naturally align people and processes, ensuring clarity and mutual understanding even in technically dense contexts.
What I deliver:
-
Actionable Data Products That Drive Decisions: At University of Tennessee Knoxville, I delivered integrated, automated dashboards and reporting workflows that enabled leaders to make faster, data-informed decisions. My work didn’t just add numbers to a dashboard — it provided clarity in ambiguity.
-
Time & Cost Savings Through Automation: At the Center for Translational data Science, I cut data processing time by 50% through automated cleaning and validation systems. This wasn’t just a workflow improvement; it freed up critical staff time for higher-value tasks and reduced data integrity issues in vital cancer genomics research.
-
Operational Efficiency Through Digital Transformation: At the State of Tennessee, I replaced over 100 pages of paper reports with interactive dashboards. This transition wasn’t merely digital; it transformed how teams consumed information, prioritized actions, and monitored safety outcomes.
-
Knowledge Infrastructure for Future Growth: Beyond immediate project deliverables, I consistently leave organizations better prepared for the future. From building a cell culture unit at the Research Institute of Forests and Rangelands to authoring technical documentation at the Center for Translational Data Science, I ensure that improvements are scalable and repeatable.
What I am most proud of:
-
Award-Winning Dashboard Development: At the State of Tennessee, my creation of interactive dashboards modernized reporting, improved user experience, and earned me Pay for Performance recognition — a rare accolade in a government data role.
-
Establishing an End-to-End Data Quality System in Bioinformatics Research: At the Center for Translational Data Science, I not only automated cleaning pipelines but also resolved systemic data integrity issues in genomic databases — directly improving data reliability for cancer research.
-
Building a Biotech Research Unit From Scratch: At the Research Institute of Forests and Rangelands, I established a cell culture unit and led conservation projects on endangered species. These efforts culminated in a peer-reviewed Springer publication — a career milestone blending science and operational leadership.
-
Mentorship That Lasts: Over the years, I’ve mentored numerous students, several of whom progressed into leadership roles. I measure success not only by my own achievements but by those I’ve helped lift along the way.
Why hiring me?
I offer a rare blend of technical rigor, process intuition, and people-centered leadership. I’m not just someone who builds dashboards — I build systems, relationships, and narratives that turn data into decisive action.
If you’re seeking a data professional who thrives in fast-paced, cross-functional environments, who’s as comfortable cleaning a messy dataset as presenting to executives, and who aligns with mission-driven, outcome-focused cultures — that’s me.
I’m drawn to organizations that value clarity, efficiency, and impact, and I deliver all three. My track record in public health, education, biotech, and traffic safety analytics proves that I adapt quickly, deliver consistently, and elevate the people and systems around me.