KAHLIA PINKINS
Data Scientist. Business Intelligence Specialist. Statistical Modeler.
Coding Junkie. Cat Lover. French Enthusiast.
Get to Know Me
I'm Kahlia, a data scientist at NYU Langone Health where I build predictive models, automate workflows, and design intelligent tools to solve complex problems in healthcare operations. From time series forecasting for emergency department staffing to deploying scalable data pipelines with Python and Airflow, my work bridges statistical modeling and real-world impact. I specialize in turning chaotic data into structured, decision-ready insights — always with a focus on practical, measurable outcomes.
Data Gathering/Mining
Knowing how and where to find important and relevant data is one of the most important aspects of being a data scientist. This is why I specialize in gathering and mining and compiling large datasets from several sources through online exploration, API's, data scraping, and more. I have excellent research skills and can pull in and manipulate data easily using softwares such as Oracle, SQL, Excel and Python.
Data Visualizations & Exploration
In today’s changing landscape, data is driving decisions for all businesses, not just tech. That's why I have the capacity to create beautiful visualizations and dashboards using Tableau and PowerBI to convey data clearly and holistically to clients in any field.
Statistical Analysis
The heart of finding data-driven solutions is statistical analysis. I use statistical analyses such as cluster analyses, regression analyses, discreet choice models, marketing mix models, SARIMAX forecasting, and many more to tell me more about the data and what future trends the data is pointing toward. This allows me to give the best advice to clients based on the data.
Data Cleaning
Data is incredibly messy by nature, there's so much data out in the world, and as a data scientist it is important to be able to create uniform, clean, and readable datasets even from billions of rows for analysis. With tools such as Python's Pandas and SQL, I can clean and manipulate a dataset with millions of rows and extract only the most important data for my analyses.
DBMS & SQL
Databases and DBMSs are invaluable tools to keep clean, accessible records of up to millions of points of data. As a data scientist, I am able to create normalized databases containing tens of millions of rows using Oracle and SQL for easily accessible and well-organized data.
Automation
Good data science isn’t just about building models — it’s about building systems. I use tools like Apache Airflow to automate data pipelines, schedule complex workflows, and ensure reliable, repeatable processes. Whether it's daily ETL jobs, real-time alerts, or long-term forecasting workflows, I streamline operations so insights aren’t just accurate — they’re always on time.