Data Analyst

GitHub 🔗|Tableau 🔗

Technical Skills: Python, SQL, R, Tableau, Power BI

Education

• Masters in Data Analytics

  Northeastern University

• Master of Science in Physics

  Pune University

• Bachelor of Science in Physics

  Pune University

Work Experience

Data Science Intern @ Bristol Myers Squibb (Jul 2025 - Sep 2025)

• Analyzed biomarker and neuroinflammation datasets in R using EDA and statistical testing to support experimental decisions.
• Converted manual Excel models into reproducible R pipelines, reducing errors and saving 40 hours of manual work weekly.
• Collaborated with scientists to validate assumptions, interpret results, and translate analyses into actionable insights.

Data Analyst @ Madden Global Solutions (Jan 2025 - July 2025)

• Designed and implemented a Python-based ETL pipeline using pandas to automate Circana data processing into Google Looker Studio for a BI reporting system from scratch to track weekly KPIs. Enabled real-time reporting for 14 clients and reduced manual reporting by 80%.
• Built an integrated supply chain analytics platform using Excel Macros to achieve 98% in-stock rates and a 15% sales increase.
• Implemented a cost-benefit analysis framework using Excel to evaluate promotional campaigns, delivering a 235% ROI.
• Automated Excel-based financial budget watch reports by extracting and transforming SAP data to track $76 million in CPG shipments.
• Identified supply chain and compliance gaps at the store level, analyzing POS data using Excel, and recovered $3.9 million in lost sales for a client.

Graduate Teaching Assistant @ Northeastern University (Apr 2024 - Jul2025)

• Provided academic support to 160 students in Machine Learning and Statistics, focusing on GLM, KNN models, regression, regularization, and hypothesis testing using Chi-Square, ANOVA, T-tests, etc., through personalized and group study sessions.
• Guided 60 students in understanding Hadoop Distributed File System (HDFS), and big data analytics using tools like Cloudera, Apache Spark, Apache Hadoop, Hue, and Impala, contributing to 70% of students achieving an A-grade.
• Guided students on AI governance and responsible AI, covering bias, fairness, and evaluation frameworks.
• Tutored 120 students in Probability and Statistics, statistical hypothesis testing and designing experiments for A/B testing.

Research Analyst @ Northeastern University (Oct 2024 - Apr 2025)

• Processed and cleaned a high-volume dataset of 5 million job postings in R by deduplicating, normalizing, and restructuring records while performing validation and compression, optimizing storage efficiency by 80% and enabling scalable analysis.
• Utilized data mining to extract hidden credentials from unstructured job descriptions using NLP in R, ensuring data integrity for accurate credential demand analysis.
• Transformed data using Alteryx and built Tableau dashboards to track credential vs. degree demand metrics and trends.

Product Analyst @ Infinity Learn (Oct 2022 - Apr 2023)

• Designed Generative AI workflows to test content variants and reduce production timelines by 40% with automated pipelines.
• Performed rigorous data quality validation in Excel across 6,000+ assessments and 500+ articles using standardized audit logs.
• Analyzed competitor platforms and engagement metrics, identifying content gaps that increased user engagement by 14%.

Product Manager @ LIDO Learning (Apr 2022 - Aug 2022)

• Led a cross-functional curriculum development team of 6 using JIRA to release digital learning products, earning a 3.9/4 rating.
• Analyzed LMS data using SQL and built Tableau dashboards informing UX decisions, increasing engagement by 20%.
• Conducted competitor and sentiment analysis on customer feedback, identifying product gaps that guided release of 3 features.

Tutor Trainer @ LIDO Learning (May 2021 - Mar 2022)

• Mentored 200+ teachers and 400+ Business Development Associates, elevating instruction quality and resulting in improved customer retention and 18% new customer growth.
• Analyzed Tutor data using advanced Excel, created dashboards using Power BI to develop an Online Teaching Practices program using Articulate Rise, resulting in a 30% increase in tutor delivery ratings and driving a 15% revenue growth within a month.

Curriculum Designer @ LIDO Learning (Oct 2019 - Apr 2021)

• Designed and developed immersive EdTech products, collaborating with the product team on strategy and research, resulting in highly engaging educational content that achieved a 3.95/4.00 stakeholder rating.
• Collaborated with the Data Analytics team to gather student data using LMS and perform analysis to drive student growth by 12%.
• Mentored and onboarded 4 new curriculum designers and helped them achieve a rating of 3.80/4.00 in their first month.

Program Manager @ Science for All Foundation (Jun 2017 - Sep 2019)

• Managed stakeholder relationships and facilitated communication between the organization and 20 low-income public schools across the city, ensuring alignment of services throughout the academic year.
• Implemented a comprehensive training program for 35 instructors, enhancing Math and Science delivery in Public Schools, resulting in improved academic performance and a 150% increase in client base.
• Led yearlong boot camp interventions in 30 low-income public schools to increase the basic math operation skills of middle school students by 65%.
• Organized the “Pune Science Festival 2018,” a two-day science exhibition, with the assistance of over 50 public school student volunteers, drawing in a crowd of over 2,500 visitors.

Projects

Engaging Worlds, Gold Medal - MIT Education Hackathon ‘24 – Python, Convai, Anthropic

Link

• Developed an AI-powered immersive learning platform that integrates interactive experiences with automated assessment across multiple devices, including VR.
• Integrated NLP for real-time student interaction analysis, generating actionable insights for educators.

Emergency Room Performance Dashboard – Databricks, PySpark, SQL, Tableau

Link

• Built an end to end analytics pipeline in Databricks to process ER visit data and analyze patient flow from arrival to discharge.
• Designed a star schema with fact and dimension tables to support analysis of wait time, length of stay, and delay patterns.
• Performed data cleaning and transformations using PySpark and SQL.
• Developed Tableau dashboards to identify bottlenecks, peak hours, and patient level trends.

Retail Sales Analytics Pipeline and Dashboard – Azure, Databricks, SQL, Power BI

Link

• Built an end to end retail analytics pipeline using Azure Data Factory concepts, Azure Data Lake, and Databricks to process data from multiple sources.
• Implemented medallion architecture with Bronze, Silver, and Gold layers to improve data quality and support scalable data processing.
• Performed data transformations and aggregations using SQL to generate business metrics such as total sales, product performance, and store level insights.
• Developed an interactive Power BI dashboard to analyze sales trends, top products, and regional performance across stores and customers.

• FIFA Players Analytics – R, Excel

  Link

• Conducted extensive Exploratory Data Analysis (EDA) on 18,483 FIFA player records, identifying key correlations and patterns in player attributes, market values, and wages.
• Developed a Logistic regression model to classify players with high or low wages with a 0.93 AUC score and a regularization model to predict players’ potential ratings with 98.92% accuracy using R.
• Performed hypothesis testing to compare overall ratings between European and South American players, revealing statistically significant differences (p-value <0.05) and providing insights for regional scouting strategies.

Kidney Failure Production – Python, SQL, Excel

Link

• Led a team of 4 members to build a Kidney Failure Prediction model using Logistic Regression and GBT models with 95.6% accuracy.
• Combined 6 datasets related to demographics, medical history, lab test, diet of the patients with over 143 variables using SQL to create train and test datasets to build a model.

NYPD Crime Analysis – Excel, Tableau

Link

• Discovered that 20% of male perpetrators involved in molestation-related crimes are young adults after performing data cleaning and Exploratory Data Analysis (EDA) using Excel.
• Developed interactive Tableau dashboards connecting various data sources and defining calculations to provide crime insights.

Drug Misuse Database Management System – SQL, R, Excel

Link

• Developed SQL database design to study drug consumption among different age groups over the period and deployed it on Azure.
• Utilized Excel for data transformation and R for data visualization of drug consumption patterns.

Analysis of Magneto Hydrodynamic Waves and Energy Transport in the Solar Corona - IDL

Link

• Investigated the coronal heating problem using Magneto-Hydrodynamics (MHD) to study energy transport and dissipation via waves in the solar atmosphere.
• Analyzed properties of propagating waves in the solar corona using data from the Solar Dynamics Observatory (SDO). Performed spatial and temporal image analysis on multi-wavelength observations using Interactive Data Language (IDL) and SolarSoft.
• Conducted Fourier analysis to study frequency distributions and power spectra at various coronal heights.