Supriya Gir

Data Analyst · Berlin, Germany

Supriya
Gir

I'm a data analyst with a background in software development, which gives me a deeper understanding of how data is created, structured, and managed before it reaches analysis. I use that perspective to build reliable analyses, uncover actionable insights, and create data-driven solutions that help businesses make better decisions.

View Projects Get in Touch Download CV
4+
Years of experience
500+hrs
Bootcamp training
10+
End-to-end Data Analytics projects
5
Industry certifications
SQL Python Power BI Tableau Machine Learning Streamlit B2 German EU Work Auth.

About me

I'm a data analyst who genuinely enjoys digging into messy datasets and figuring out what's actually going on. I work with SQL, Python, Excel, and Power BI - not because they're on a list, but because they help me build things that are useful: clean dashboards, automated reports, and analysis that people actually act on.

I care a lot about data quality. A wrong number in a report is worse than no number, and I've learned that the hard way across 4+ years working in enterprise systems at Capgemini, client projects in Dubai, and now an intensive analytics bootcamp in Berlin.

I work well with people across teams - whether that's translating a business question into a SQL query or walking a non-technical stakeholder through a Power BI dashboard. I'm based in Berlin, fluent in English, and conversational in German (B2).

Certifications

  • Data Analytics Bootcamp - Ironhack Berlin 2026
  • Microsoft Certified: Power BI Data Analyst Associate Apr 2025
  • Tableau Certified Data Analyst Mar 2025
  • Google Data Analytics Professional Certificate Jul 2025
  • B.E. Computer Science - Pune University 2009

What I work with

Technical skills

Visualization

Power BI Tableau Tableau Advanced Data Storytelling Python Visualization Streamlit Excel

Programming

Python Pandas NumPy Scikit-learn Seaborn Matplotlib Web Scraping APIs

Databases

MySQL SQL Server DB2 CTEs Window Functions SQL Joins & Subqueries SQL-Python Integration

Analytics

KPI Reporting Forecasting A/B Testing ETL Feature Engineering Hypothesis Testing Statistical Concepts Univariate & Bivariate Analysis Data Exploration

Machine Learning

Random Forest KNN Gradient Boosting Unsupervised Learning Supervised Learning Ensemble Methods Hyperparameter Tuning Imbalanced Datasets

Cloud & Tools

Azure Data Factory Power Automate GitHub VS Code Cloud Computing Git Collaboration Environments

Portfolio

Selected projects

Presentation ⬈ Live App ⬈ Github ⬈
01

Mental Health in Tech — Employee Stress Prediction

End-to-end ML pipeline predicting employee stress levels from survey data. Achieved 80.95% accuracy with Random Forest. Deployed as a live Streamlit app for real-time support recommendations.

Python Scikit-learn Random Forest KNN Streamlit Supervised Learning
Mental Health ML Project
Presentation ⬈ Github ⬈
02

US Hospital Cost & Quality Analysis

Analyzed 1.5M+ Medicare-certified hospital records to surface relationships between care quality, pricing, and reimbursement. Identified "Hidden Gem" hospitals: 5-star quality at below-average cost.

Python MySQL CTEs Aggregation
US Hospital Cost Analysis
Presentation ⬈ Live App ⬈ Github ⬈
03

Electric Vehicle Market Analysis

Explored EV market data to surface pricing trends, regional adoption patterns, and purchase drivers. Delivered interactive Power BI dashboards filterable by segment and geography.

Python Power BI EDA
EV Market Analytics Dashboard
Presentation ⬈ Live App ⬈ Github ⬈
04

Book Recommender Application

Personalized book recommendation app using collaborative filtering and content-based ML techniques. Deployed via Streamlit for live user interaction and discovery.

Python Streamlit Collaborative Filtering ML
Book Recommender Application
Presentation ⬈ Github ⬈
05

Satellite Data Exploratory Analysis

Developed a Satellite Exploratory Data Analysis (EDA) project using Python, Pandas, and Power BI to analyze global satellite data from multiple sources. The project involved cleaning and merging datasets, exploring satellite launch trends, orbit distribution, countries, operators, and mission purposes, and creating an interactive dashboard to present key insights. The analysis highlighted the rapid growth of LEO satellites, the dominance of communication satellites, and the increasing challenge of space debris.

Python Power BI EDA Data Storytelling
Satellites EDA Dashboard
Github ⬈
06

Microsoft Fabric End-to-End Data Pipeline

Built an end-to-end **Data Engineering** solution using **Microsoft Fabric** to automate the ingestion, transformation, and reporting of monthly sales data. The project implements a **Medallion Architecture (Bronze, Silver, Gold)** with PySpark, Delta Lake, and Fabric Pipelines for incremental data processing. The final Gold layer powers an interactive Power BI dashboard, delivering business insights through KPIs, sales analysis, and automated reporting.

Microsoft Fabric PySpark Power BI Medallion Architecture Data Pipelines Lakehouse
Microsoft Fabric Data Pipeline

More work

Online Retail Sales Analysis
SQL data cleaning + Power BI dashboard on 1M+ e-commerce transactions. Regional trends, seasonality, and customer segmentation.
SQL Server Power BI CTEs Window Functions
View
Healthcare Analytics
Patient flow, bed occupancy, readmission rates, and staff-to-patient ratios across 10 departments using SQL and Power BI.
SQL Server Power BI DAX Healthcare
View
Supply Chain Analytics
End-to-end supply chain performance analysis covering inventory, logistics, and supplier metrics with actionable dashboards.
SQL Power BI Supply Chain
View
Job Market Analysis
Explored hiring trends, in-demand skills, and salary patterns across data roles to surface actionable insights for job seekers.
Python EDA Power BI
View
Retail Sales Dashboard
Interactive sales performance dashboard tracking KPIs, regional breakdowns, and product trends for a retail business.
SQL Power BI KPI Reporting
View

Career

Work experience

Mar 2026 – Jun 2026
Ironhack Berlin
Data Analytics Bootcamp · Berlin, Germany
  • Completed 500+ hours of intensive training in SQL, Python, Machine Learning, Power BI, and Tableau.
  • Built and deployed 5 end-to-end analytics and ML projects including a live Streamlit prediction app.
Jan 2021 – Apr 2023
We Developers
Data Consultant (Project-Based) · Dubai, UAE
  • Designed and developed full-stack websites with Python and Django, with backend database integration using MySQL.
  • Managed cloud hosting and deployment, ensuring secure backend and database connectivity.
  • Structured and maintained relational databases to support efficient data storage and retrieval.
  • Analyzed survey results for a research project using Python (Pandas) and built a desktop application with Tkinter to display the findings.
Mar 2010 – Oct 2014
Capgemini
Associate Consultant · Pune, India
  • Maintained and enhanced enterprise financial applications for large-scale clients, translating requirements into reliable system improvements.
  • Performed SQL-based data validation across dev, test, and production environments ensuring data integrity for mission-critical workflows.
  • Led a system optimization project that drove a 150% increase in throughput - earning the Spot Award for outstanding impact.
  • Mentored 10+ juniors for DB2 certification - recognized with the Silver Star Award for knowledge-sharing excellence.

Get in touch

Let's work together

Open to data analyst roles in Berlin and across the EU. Let's talk.

supriyagosavi14+portfolio@gmail.com LinkedIn GitHub