Vinay Vaida

Masters of Science in Data Science

May 2024

University at Albany, SUNY

GPA: 3.7/4

Coursework: Topological Data Analysis, Machine Learning, Deep Learning, Applied Statistics using R, Linear Algebra, Optimization

Research Scientist II

January 2024 - June 2025

New York State Department of Health, Albany

• Division of Science and Technology
• Predictive Modeling: Developed and implemented a K-means clustering model to detect anomalies in file submission patterns of Universal Public Health Node database, enhancing monitoring capabilities by effectively identifying irregular behaviors based on submission time, submitter, department, and payload size.
• Data Exploration and Interpretation: Conducted rigorous data mining and feature engineering on a 238 million row UPHN database, uncovering inconsistent monthly file submission trends that improved data-driven decision-making.
• Data Visualization: Forecasted incorrect file submissions from 2016 to 2023 with 94% accuracy using time series. Created Tableau visualizations to illustrate submission trends, enabling stakeholders to interpret anomalies and make informed, data-driven decisions.
• Patient Claims Analysis: Analyzed over 2M patient claims with SAS PROC SQL across payers, facilities, prescriptions, and medication expenses, uncovering equity gaps in medication access and reimbursement trends by income, race, gender, and disability to inform policy and access decisions via interactive dashboards.
• Wadsworth Clinical Research Center
• AI-Driven Pathogen Detection: Designed and deployed AI model using DNA sequence text data (NLP) to identify harmful fungi, classifying 386+ samples in under 3 seconds with 0.98 precision and improving outbreak tracking across eight Northeast U.S. states.
• Automated Clinical Pipeline: Engineered a Streamlit-based cloud tool on GCP using Docker and Python with a drag-and-drop GUI for automated DNA analysis, enabling non-technical users to run complex workflows easily and cutting processing time by 95%.
• Data Warehousing: Developed Python pipeline integrating 2.95M records from multiple sources to automate monthly updates for NYS DOH's Candida auris Tableau dashboard, enabling real-time case monitoring across the Northeast U.S. states.
• MycoSNP Pipeline: Streamlined weekly GCP pipeline runs (Java & Python) on patient samples, applying K-means and hierarchical clustering to trace Candida auris transmission and support real-time outbreak reporting with CDC.

Data Analyst

February 2021 - July 2022

Cognizant Technology Solutions, Hyderabad

• Data Mining and Business Analytics: Mined and analyzed structured and unstructured data from various company databases including product shipment logs, manufacturer costs, and wholesale pricing, driving optimization of marketing techniques and product development.
• Model Selection and Evaluation: Collaborated in an agile manner with a cross-functional team of 7 for model selection, testing, and evaluation. Assessed the impact of variables and features on model efficiency to formulate analysis for feature selection, parameter tuning, pricing strategy refinements, and A/B testing.
• Custom Algorithm Development: Applied regression and multivariate data analysis using Python, SQL, and R to develop custom models and algorithms to optimize product profitability, enhancing data-driven decision-making by 20%.
• Time Series Forecasting: Established and executed 3+ time series forecasting models to estimate future sales and shipment volumes, drawing on past trends of historical sales and logistics data and encompassing data spanning thousands of rows.