Professional Experience
Machine Learning Engineer & Data Scientist Co-Op
RXA: AI & BI Consulting —–
- Website
- January 2021 – Present
- Developed Gradient Boosted ML Model on custom dataflow in DOMO [SQL, Python] structuring 60,000+ sales records optimizing client automotive acquisition for maximizing expected profit margin with 96% accuracy
- Created API [Python, Google Cloud API] to aggregate and structure ~4GB historic client sales CSV data from drive repository for 100+ files with full client encryption and recurring database updates saving ~30+ hrs. data entry
- Implemented ML hierarchical clustering model [Python, R, AWS Sagemaker] on client’s insurance case data with AUROC of 0.88 thus identifying 7 key consumer risk factors potentially increasing policy profit margins 30%
Machine Learning Dev. Student Research
Computational Ecology, Evolution and Biology Lab - University of Michigan —–
- Lab Website
- January 2020 – Present
- Published open-source R package titled weightedClustSuite [R, C++, Python] for Machine Learning Density Clustering & Validation, used on weighted species abundance data enabling identification of species distribution clusters Link
- Applied weighted Species Trait Data to 2014 ML Research in Density Peak Clustering demonstrating contrary coexistence of similar niched species despite competitive exclusion with promising clustering validation (DBI: 0.56)
- Operate as an interdisciplinary reference within lab to explain and analyze machine learning and data analysis research. *My Code
Product Director & Founder
Michigan Eco Data —–
- Org Website
- September 2019 – Present
- Product Manager Execution of consumer heatmap awarded 2000$ sponsorship by Michigan Institute of Data Science (MIDAS)
- ● Built dynamic web dashboard software of interactive Michigan Heatmaps [HTML, JS, Python] (My Code) from 400,000+ Unstructured EPA data points for Michigan Residents to identify contaminants at high levels in their zip codes
- Founded org as a venue for interdisciplinary exploration in data science, software engineering, and environmental conservation
- Other Projects Include: Ecological Footprint App Tracking and Wildlife Drone Pattern Analysis
- Notable Technologies Used: Python [Pandas, Date-Time Forecasting, PyPlot, Matplotlib], R, HTML, CSS, Jinja, GitHub Pages, Swift, MAVSDK
Data Science Intern
GHD: Engineering, Architectural, and Environmental Consulting —–
- Company Website
- June 2019 – August 2019
- Implemented Automation pipeline [Python, FME] from custom field forms into my designed database [SQL] auto filling Client Audits resulting in an 80% reduction in manual data entry for Client EPA Facility Audits
- Deployed ML: Random Forest & Regression Models on structured ARCGIS data determining optimal PFAS site testing order for estimated 75% reduction in location sampling costs
- Notable Technologies Used: ARCGIS, ARCGIS External API, SAP-HANA, Python, Survey123, FME, MS Excel
Machine Learning & Computer Vision Student Research
Michigan Medicine Computer Aided Diagnosis Laboratory - University of Michigan —–
- Lab Website
- January 2017 – May 2019
- Findings resulted as Primary Author in two Publications, was selected for Poster, Oral Presentation in SPIE Conference 2019
- Performed Feature Extraction and Selection on Bladder CTU Scan Segmentations to extract key features in Bladder Cancer Lesion Staging (staging determines the avenue of treatment)
- Implemented and trained a series of Back Propagated Neural Networks, Linear Discriminant Analysis, Support Vector Machines, and Random Forest Algorithms – validated through ROC analysis - with 92% suite ROC Sens. Accuracy for accurate staging diagnosis of Bladder Cancer determining immediate treatment
- Notable Technologies Used: C++, C, Python, Weka, MS Excel
- My Work Samples