About me

I am a Data Scientist & Software Engineer with a passion for transforming complex data into actionable insights and building stellar Web applications. With a master’s degree in Data Science & Bachelor's in Computer Engineering, I bring expertise in machine learning, data visualization, ETL pipelines, and Web development.

My experience spans building predictive models like customer churn and attrition analysis, developing interactive dashboards in Power BI and Looker, optimizing pipelines with tools like Airflow and Snowflake, and building scalable web apps using .NET, Angular, as well as modern frameworks like React. I have a solid foundation in Python, R, SQL, and cloud platforms like AWS and GCP. I aim to solve challenging problems at the intersection of data and business to drive measurable impact.

What I do

  • design icon

    Data Engineering

    ETL including orchestration with DAGs.

  • Web development icon

    Data mining & Analysis

    Using Data to answer questions.

  • mobile app icon

    Machine Learning

    End to End ML solutions inlcuding ML OPs.

  • camera icon

    Software Development

    I make high-quality web apps at a professional level. (.NET, Angular, Node.js, React)

Resume

Education

  1. Indiana University - Bloomington

    2022 — 2024

    GPA : 3.97

    Course Work : Statistics, Data Vizualization, Applied Machine Learning, Cloud Computing, Advanced Database Concepts, Sport Analytics

  2. Mumbai University

    2017 — 2021

    GPA : 3.4

    Course Work: System programming, Data Structures and Algorithms, NLP, OS

Experience

  1. Data Analyst

    June 2024 — Present
    • • Predicted volunteer turnover using Random Forest classifier with SMOTE oversampling, achieving a recall of 89% in identifying at-risk volunteers and expected to save an estimated $120K in recruitment and training expenses annually.
    • • Performed descriptive analysis, facilitating data-driven strategies that resulted in a 25% reduction in volunteer attrition.
    • • Developed an interactive Power BI dashboard using DAX and Power Query for data transformation, enabling tracking of metrics like attrition rate, volunteer satisfaction levels, volunteer hours per capita, and engagement score.
    • • Engineered an ELT pipeline using DBT, leveraging Airflow DAGs for orchestration, creating a centralized data warehouse in Snowflake, including DBT data tests and macros for data quality checks reducing data preparation time by 60%.
  2. Data Analyst

    Aug 2023 — May 2024
    • • Identified populations and areas facing energy insecurity by performing EDA on Power Outage data via Excel & Tableau.
    • • Engineered a web application using Plotly Dash to visualize grid resilience variations across different regions and times, identifying impacts of utility disconnections, as well as aiding leadership in making decisions for equitable energy policies.
    • • Utilized PySpark to merge 1000+ files into cohesive datasets, reducing latency for creating visualizations in the web app.
    • • Improved Geo dashboard loading time using Mapshaper to reduce polygon complexity, resulting in 70% faster visualization.
  3. Software Engineer

    May 2021 — June 2022
    • • Automated requisition mapping for pre-approved workflows by building an ETL pipeline in C#, integrating micro-services via REST APIs for data retrieval and loading into SQL Server databases, resulting in 90% faster purchase order creation.
    • • Developed RESTful API to send expenditure data from the B2B e-procurement platform, facilitating spending analysis.
    • • Created stored procedures in SQL to dynamically filter products based on user-selected criteria, reducing latency by 50%.
    • • Deployed 35 critical releases across 3 environments with 100% success rate by leveraging Azure DevOps CI/CD pipelines.
    • • Collaborated with a cross-functional team under a strict Agile (scrum) environment leveraging JIRA and Confluence, ensuring productivity and timely completion of milestones.

Portfolio

Contact

Contact Form