Nikita Amin
Data Analyst & Biostatistician
Scientifically-minded and academically trained data analyst utilizing my biological research background to bring a unique and rigorously thorough perspective to the world of data-driven decision-making
About Me
I am a recent graduate of the University of Virginia College of Arts & Sciences with a newly completed certification in Data Analytics from General Assembly.
I have been honing my skills in statistical data analysis since my time at the Loudoun Academy of Science, a magnet high school specializing in research and STEM. My exposure to the importance of the ability to clean, analyze, and present data-driven conclusions continued at U.Va while pursuing my degree in Biology. Upon graduation, I realized that my passion was beyond the lab environment, and instead in the ability to deliver actionable insights that contribute to the understanding of human health.
Technical Skills
Data Analysis · Data Visualization · Data Cleaning · Web Scraping · Pivot Tables · Data Modeling · Data Wrangling · Big Data Utilization · Linear Regression · Machine Learning · Statistical Modeling
Programming Languages and Libraries
Python · JavaScript · R (programming language) · SQL · Tableau · PostgreSQL · pgAdmin · Power BI · Microsoft 365 · Excel · PowerPoint
Scientific & Laboratory Experience
Clinical Research · Data Collection · Scientific Writing · Research Design · Biomedical and Biological Sciences · Health Communication · Clinical Data Analysis · Biological Assays and Analyses
Python Libraries:
Pandas · NumPy · Matplotlib · Seaborn · Beautiful Soup · Plotly · Jupyter
Python Regression Models:
Linear · CatBoost · RandomForest · KNeighborsClassifier · Polynomial (NumPy) · Always learning more!
Projects
These projects served as both an application and demonstration of my data analysis skills across platforms, always drawing from strictly real-world data
Slide decks are designed using a combination of custom graphics and free-to-use SlidesGo templates
Predicting Parkinson’s Progression
- The goal of this project was to evaluate the ability to predict the symptom progression of a patient based on their protein expression scores, as measured using blood samples
- Accurate modelling would benefit patients by elucidating some of the mysteries of what is currently an unpredictable disease, as well as advancing our understanding in order to progress towards better treatments and a possible cure
- Dataset: Clinical patient data of symptom severity overtime
Wind Turbine Investment Analysis
- A presentation for a hypothetical board of investors looking to invest in wind turbine energy production, presenting a nationwide analysis of all wind turbines in the U.S. and the advantages to investing in the growing sector
- Selected by instructors as 1 of 3 team leaders, played the role of scrum master following the Agile workflow overseeing the team of 5
- Created using Python to clean data and Tableau for visuals
- Dataset: USGS Wind Turbine Database & EIA Turbine Operator Data
United Kingdom’s Gender Wage Gap
- An analysis of the gender wage gap in the United Kingdom, investigating contributing factors and possible solutions
- Created using SQL to clean and query data and PowerBI for visuals
- Dataset: U.K. Government Reporting uploaded to pgAdmin
Keys to Kickstarter Success
- Exploring how to optimize a Kickstarter fundraiser in order to reach (and surpass!) donation goals
- Created using Excel to clean data and Tableau for visuals
- Dataset: Historical campaign data provided by course
Nikita Amin's Portfolio 