Hey, I'm Nirvika

I'm a Data Analyst

Transforming Complex Data into Actionable Insights to Drive Strategic Decisions and Business Impact.

About Me

I'm a data analyst who loves solving analytical problems using SQL, Python, visualization tools, and statistical logic. I specialize in building dashboards, crafting data pipelines, and uncovering patterns in financial, operational, and research datasets.

I enjoy taking raw, messy data and transforming it into something beautiful — dashboards, insights, stories, and strategies that help organizations make informed decisions. I’ve worked across education, finance, and enterprise engineering environments.

My mission is simple: make data understandable, actionable, and impactful.

Skills & Abilities

Programming Languages

Python

Data Analysis & Visualization

Pandas

NumPy

Matplotlib

Seaborn

Tableau

Power BI

Excel

Statistics & Machine Learning

Hypothesis Testing

Regression Analysis

Classification

Clustering

Scikit-learn

Statsmodels

Databases

PostgreSQL

MySQL

SQLite

Data Cleaning & ETL

Pandas Data Cleaning

Data Transformation

ETL Pipelines

Rest APIs & FastAPI

Cloud & Tools

AWS

Azure

Git & GitHub

Docker

Soft Skills

Team Collaboration

Communication

Problem Solving

Time Management

Experience

Data Analyst (Digital Scholarship Services)

Albin O. Kuhn Library & Gallery – UMBC

January 2026 – Present

Applied advanced Python programming and data analysis to perform quality assessments, validation, and anomaly detection across scholarly datasets.
Cleaned, transformed, and structured raw data for ingestion into ScholarWorks@UMBC, ensuring accuracy and analytical readiness.
Automated data correction and preprocessing workflows using Python, increasing efficiency and reducing manual effort.
Troubleshot and enhanced Python-based data pipelines and interfaces to support repeatable and scalable data operations.
Maintained data integrity and reliability to support institutional reporting, analytics, and research visibility.

Data Analyst (Digital Library Repository)

UMBC Albin O. Kuhn Library & Gallery – Baltimore, MD

June 2024 – Dec 2025

Managed and refined 34,000+ scholarly records in the MD-SOAR repository, ensuring data integrity and compliance with metadata standards.
Implemented Python scripts and Excel workflows to automate metadata conversion, validation, and cleaning, reducing manual effort by 70% and improving data accuracy.
Standardized Dublin Core metadata in collaboration with librarians, enhancing research discoverability and reporting efficiency.
Performed data audits and validation to identify inconsistencies, strengthen data governance, and ensure high-quality metadata.

Software Developer

LTIMindtree (Client: Credit Corp Group, Australia) – Bengaluru, India

August 2021 – November 2023

Developed high-performance RESTful APIs using ASP.NET Core Web API, validated with Postman, improving API response times and execution efficiency by 45%.
Designed and implemented secure microservices architectures with JWT authentication, reducing security vulnerabilities by 70% and ensuring fault-tolerant backend services.
Optimized MSSQL databases using indexing, stored procedures, triggers, and complex LINQ and Entity Framework Core queries, improving query performance and data access speed by 30%.
Built synchronous and asynchronous REST APIs to handle high-volume concurrent transactions, enhancing system scalability, responsiveness, and reliability.
Designed and deployed CI/CD pipelines using Octopus Deploy, Git, and Azure DevOps, enabling zero-downtime biweekly releases and reducing deployment time by 40%.
Executed unit and integration testing with NUnit, along with API validation and regression testing using Postman, increasing test coverage and code reliability by 40%.
Implemented monitoring and logging pipelines and provided production support by debugging backend services, resolving critical issues, optimizing performance, and accelerating incident resolution.
Collaborated in Agile/Scrum teams using Jira and TFS for sprint planning, work item tracking, and code reviews, consistently achieving 100% on-time sprint delivery.

Education

Masters of Professional Studies in Data Science(M.P.S)

University of Maryland, Baltimore County

Jan 2024 – Dec 2025

CGPA: 3.9 / 4.0

Focused on data analysis, predictive modeling, and end-to-end data science workflows with an emphasis on actionable insights and scalable solutions.
Completed advanced coursework in Data Management, Big Data & Platforms, Machine Learning, Financial Data Science, and Project Management.
Led a capstone project analyzing student start-up success metrics and predicting outcomes using Python, Pandas, Scikit-learn, and Streamlit for interactive dashboards.
Developed data-driven solutions including ETL pipelines, predictive models, and interactive dashboards to support decision-making.
Strengthened core skills in statistical analysis, feature engineering, model evaluation, and data visualization using Python, Power BI, Tableau, and SQL.

Bachelor of Engineering in Computer Science(B.E)

Dayananda Sagar Academy of Technology and Management

August 2017 – July 2021

CGPA: 8.72 / 10.0

Built strong foundations in Data Structures & Algorithms (DSA), Object-Oriented Programming (OOP), Software Engineering, Cloud Computing, Advanced Python Programming, and Database Management Systems (DBMS).
Created a Computer Vision Based Mouse Control Using Object Detection project for Human-Computer Interaction using Python, OpenCV, and PyAutoGUI. View Publication

Projects

Student Start-up Success Analysis

Analyzed 2,100 student-led start-up projects across 40 institutions using Python and Pandas. Conducted EDA, feature engineering, and correlation studies to identify key success drivers. Built an interactive Streamlit dashboard to visualize trends and support decision-making for mentorship, incubation, and funding.

Live Demo View on GitHub View on Youtube

LinkedIn Job Market Analysis

Processed 1.3M+ job listings using Apache Spark and Hive to extract labor market trends, including top skills, roles, and geographic demand. Created interactive Power BI dashboards to guide 100+ HR managers in hiring and workforce planning.

View on GitHub

EDA – Estimation of Obesity Levels

Conducted exploratory data analysis on health datasets to identify factors influencing obesity prevalence. Visualized correlations and trends using Python (Pandas, Matplotlib, Seaborn), providing actionable insights for public health recommendations.

View on GitHub View on Tableau

Portfolio & Volatility Modelling

Analyzed financial data to model risks and returns. Engineered key features, conducted statistical analysis, and built interactive dashboards with Gradio to help clients evaluate portfolio performance and market risk.

View on GitHub

Credit Card Fraud Detection (EDA)

Performed exploratory data analysis on 284K credit card transactions to identify patterns of fraudulent activity. Handled class imbalance using SMOTE and visualized key trends to inform fraud detection strategies.

View on GitHub

Airbnb Rental Price Analysis & Prediction

Analyzed NYC Airbnb listings to identify factors influencing rental prices, including location, property type, host attributes, and reviews. Performed EDA to uncover trends and correlations, and developed interpretable predictive models to provide actionable pricing insights for hosts and guests.

View on GitHub View Case Study

Netflix Content Recommendation Case Study

Case Study : Optimizing Netflix Content Recommendations

Analyzed Netflix’s recommendation system to enhance personalization and user engagement. Focused on data quality assurance—validation, cleaning, enrichment, and monitoring—while addressing missing or biased data. Proposed a hybrid Waterfall-Agile approach for iterative improvements, delivering actionable insights to improve recommendation accuracy and user retention.

View Case Study

Technical Paper : From Bytes to Better Health - Leveraging Big Data for Enhanced Remote Patient Care

Examined how big data, IoMT, and machine learning enable continuous remote patient monitoring and predictive healthcare analytics. Analyzed large-scale data processing with Hadoop and Apache Spark, evaluated predictive models for health risk assessment, and reviewed privacy-preserving techniques such as federated learning and blockchain to support secure, data-driven clinical decisions.

View Research Paper