Data Analyst adept at turning complex datasets into actionable insights, bridging technical expertise with business acumen. Proficient in SQL, Python, Excel, and Tableau, with experience in machine learning and data ware…
Data Analyst adept at turning complex datasets into actionable insights, bridging technical expertise with business acumen. Proficient in SQL, Python, Excel, and Tableau, with experience in machine learning and data warehousing.
Identified a 15% drop-off rate that led to improved participant follow-up strategies by conducting extensive data manipulation and cleansing on 20K+ records using SQL (CTEs, subqueries, window functions) and SAS.
Performed statistical analysis in R to evaluate outreach campaigns and track KPIs like engagement and attendance.
Identified a 15% drop-off rate that led to improved participant follow-up strategies by conducting extensive data manipulation and cleansing on 20K+ records using SQL (CTEs, subqueries, window functions) and SAS., Performed statistical analysis in R to evaluate outreach campaigns and track KPIs like engagement and attendance.
Performed exploratory time-series analysis on historical load profiles in Python and visualized energy usage in a proprietary software to identify peak-demand patterns and support event-day planning., Optimized portfolio delivery for Demand Response programs by managing customer enrollment, consolidating utility portal data, validating 300+ site records in Excel, and analyzing participation trends in Python., Streamlined and automated data collection for 5 energy utilities (e.g. NYSEG, PSEG) via R Shiny & Selenium scripts., Designed 4 dynamic Tableau dashboards for real-time KPI tracking, extracting data from Salesforce CRM with SQL., Reduced errors by 25% by streamlining energy records for CRM integration via Excel (PivotTable, VLOOKUP, VBA).
Performed exploratory time-series analysis on historical load profiles in Python and visualized energy usage in a proprietary software to identify peak-demand patterns and support event-day planning.
Optimized portfolio delivery for Demand Response programs by managing customer enrollment, consolidating utility portal data, validating 300+ site records in Excel, and analyzing participation trends in Python.
Streamlined and automated data collection for 5 energy utilities (e.g. NYSEG, PSEG) via R Shiny & Selenium scripts.
Designed 4 dynamic Tableau dashboards for real-time KPI tracking, extracting data from Salesforce CRM with SQL.
Reduced errors by 25% by streamlining energy records for CRM integration via Excel (PivotTable, VLOOKUP, VBA).
• Led SQL, Tableau, and database design workshops for 150+ students, enhancing practical analytics proficiency.• Mentored 15 groups to develop Data Science solutions for real-world challenges and evaluated 500+ assignments.
Saved 20% in procurement costs by optimizing inventory through root-cause analysis and statistical evaluations., Increased patient engagement by 15% through marketing campaigns informed by demographic analysis in Python., Increased patient capacity by 13% by optimizing scheduling with time-series forecasting in Python (statsmodels)., Provided key recommendations to stakeholders by analyzing data in Python and visualizing findings in Power BI.
Saved 20% in procurement costs by optimizing inventory through root-cause analysis and statistical evaluations.
Increased patient engagement by 15% through marketing campaigns informed by demographic analysis in Python.
Increased patient capacity by 13% by optimizing scheduling with time-series forecasting in Python (statsmodels).
Provided key recommendations to stakeholders by analyzing data in Python and visualizing findings in Power BI.
• Built an MLOps workflow orchestrating ETL, CI/CD, validation (TFDV), Snorkel labeling and serving 338M records.• Deployed RAG-based summarizer using OpenAI APIs and Pinecone; built Streamlit interface for product feedback.
• Designed 5 Tableau dashboards with DAX measures to analyze 164K employee records and identify industry trends.• Reduced errors by 95% by performing data pre-processing in Python using Pandas, NumPy and statistical methods.
• Improved query performance by 75% by designing a scalable database architecture using SQL and MongoDB.• Executed optimized complex SQL queries (joins, CTE, aggregations) to analyze data and uncover actionable insights.
• Achieved 79% accuracy with Naive Bayes, highest among 5 supervised ML models developed without scikit-learn.• Applied SMOTE to handle class imbalance and constructed a neural network model to validate backpropagation.
The AI-first Recruitment Operating System that unifies and automates the entire hiring lifecycle for modern enterprises worldwide.
Dr Job FZ LLC. 2026 © All Rights Reserved
