Data Analyst | Python, SQL, Power BI & Azure
I am a Data Analyst with a unique background—leveraging over 8 years of experience in civil engineering and project management to drive data-informed business decisions. I specialize in taking raw, messy data and transforming it into clear, actionable business intelligence.
I don't just write queries; I know how to ask the right business questions, manage complex workflows, and communicate technical findings to non-technical stakeholders.
- Languages: SQL (MySQL, PostgreSQL, Window Functions, CTEs), Python (Pandas, NumPy, Regex)
- Data Engineering & Cloud: Azure (Blob Storage, Data Factory, Synapse Analytics)
- BI & Visualization: Power BI (DAX, Data Modeling), Matplotlib, Seaborn
- Data Analysis: Advanced Excel (Power Query, Power Pivot, XLOOKUP), Statistical Analysis
- Objective: Architect an end-to-end data pipeline to decode hospital billing structures and uncover the clinical drivers of 30-day patient readmissions across 3M+ records.
- Tools Used: Python (Pandas, SQLAlchemy), MySQL, Power BI, DAX
- Highlights: Designed a robust Star Schema using SQL Views to resolve Cartesian grain mismatches, processed 2.2M+ lab results using memory-efficient chunking, and developed an interactive Power BI Command Center that exposed a 26.3% readmission risk cohort and validated DRG flat-rate billing models.
- Objective: Analyze holiday retail data to evaluate demographic purchasing behaviors and regional sales performance.
- Tools Used: Python (Pandas, Matplotlib, Seaborn)
- Highlights: Engineered median target encoding to evaluate categorical correlations, utilized Pandas to aggregate demographic spending patterns, and developed multivariate visualizations to uncover the crucial gap between high transaction volume and high average order value.
- Objective: Identify primary demographic purchasing drivers and uncover customer shopping patterns.
- Tools Used: Python (Pandas), SQL, Power BI
- Highlights: Engineered a data pipeline to clean and transform datasets using Pandas (handling missing values and formatting via Regex), utilized SQL to query purchasing patterns, and developed an interactive Power BI dashboard to visualize demographic trends.
- Objective: Analyze the correlation between movie production budgets, genres, and overall profitability.
- Tools Used: Python (Pandas, NumPy, Seaborn)
- Highlights: Conducted in-depth Exploratory Data Analysis (EDA) on extensive movie datasets, manipulating and structuring the data before visualizing financial and genre-based correlations using Seaborn.
- LinkedIn: https://www.linkedin.com/in/sauryayan/