Durham, North Carolina, United States
A driven data scientist that brings Python, R, SQL, and Tableau together to create high impact messages, weave stories together from data, and conduct statistical analyses. I have received multiple awards from Driscoll's for innovation, leadership, collaboration, and excellence. I have spearheaded multiple projects, and I am comfortable contributing as a team member or working independently. I am currently in my final semester of my master's degree in Statistics with machine learning specialization. In my undergraduate program at CSUMB, I received a service award for my work with the non-profit First 5, a capstone award for my work with time series data, and a scholarship for academic achievement.
• Collaborated with data scientists to optimize neuroscience data workflows on GitHub, enhancing consistency and operational efficiency across data-driven projects. • Developed dynamic, actionable data visualizations in Python (using Visual Studio) to interpret neuron activity patterns, enhancing stakeholder engagement through clear, data-driven insights and supporting decision-making. • Created an autoencoder algorithm to implement with a convolutional neural network classifier, increasing accuracy in prediction.
• Acted as the primary data science expert on the Genome Browser’s Engineering team, conducting research on their large public health data system to pinpoint sub-populations in server requests and contributors to increased execution time. • Applied advanced analytics techniques, including machine learning and artificial intelligence, to analyze extensive data collected by the Genome Browser. This research resulted in the creation of user profiles identifying heavy users and contributing to a deeper understanding of the user population. • Conducted data transformation and formulated candidate regression models to assess factors impacting server request execution time. This initiative opened new research opportunities aimed at optimizing server execution time. • Implemented student-t distributed stochastic neighborhood embedding to reduce dimensionality and visualize data in a simplified space, illustrating sub-populations of requests by specification.
• Created fruit supply visualization dashboards and developed key performance indicators adopted globally. Unified disparate data sources. • Leveraged forecast data in Monte Carlo revenue simulation, quantifying the probability of meeting targets and the amount of risk in achieving said targets for Leadership. • Improved weekly financial report, reducing the number of errors and weekly time investment to complete, while increasing ready-made features. • Planned, organized, and presented user-centric impactful visualization solutions for strategic planning, resulting in 50% greater audience of historical and projected growth.
• Prevented the loss of millions of dollars of fruit via the creation and maintenance of the labor model to help growers anticipate labor demand based on fruit volume and identify gaps in workforce supply and demand. • Coordinated with multiple districts for computing harvest speed increases, and non-harvest rates per area to implement in the labor model. • Research industries contributing to voluntary workforce attrition to quantify the future labor gap.
• Statistical analysis, including: data cleansing, exploratory data analysis, hypothesis formulation and hypothesis testing of two years of family survey data to answer questions relating to kindergarten readiness. • Presented models with predictive power on child preparedness for kindergarten aligning with First 5’s strategy to promote kindergarten readiness to executive management.