Data Analyst Power Bi

SanketKumar Patel Data Analyst

CA, USA +1-312-***-**** ***************@*****.*** LinkedIn GitHub PROFESSIONAL SUMMARY

Data Analyst with hands-on experience in financial modeling, statistical analysis, and predictive analytics across social innovation, academia, and manufacturing domains. Skilled in Python, SQL, Excel, and Power BI for building models, dashboards, and ETL workflows that improve decision-making and operational efficiency.

TECHNICAL SKILLS

Programming & Scripting: Python, R, SQL, MATLAB, PySpark, Pandas, NumPy Data Engineering: ETL Pipelines, API Integration, OLAP Queries, Data Cleaning, Data Wrangling, Data Validation, Data Transformation Databases: MySQL, PostgreSQL, MongoDB, Relational Databases, NoSQL, Normalized Database Design Business Intelligence & Visualization: Power BI, Tableau, Excel, DAX, Seaborn, Matplotlib, Dashboard Development, KPI Tracking Machine Learning & Statistical Modeling: Scikit-learn, TensorFlow, PyTorch, MLlib, XGBoost, Time Series Forecasting, Regression Analysis, Predictive Modeling, Classification, Monte Carlo Methods, Statistical Inference Analytics & Reporting: KPI Development, Ad-hoc Reporting, Automated Reporting, A/B Testing, Hypothesis Testing, Forecasting Models, Geospatial Analytics: ArcGIS, QGIS, Leaflet, Geospatial Data Analysis, Location Intelligence Big Data & Cloud: Spark (PySpark, MLlib), Distributed Data Processing, Data Pipelines Automation Collaboration & Workflow Tools: GitHub, Jupyter Notebook, VS Code, Excel VBA, Agile/Scrum, Documentation & Reporting WORK EXPERIENCE

CrowdDoing, CA, USA Mar 2025 – Current

Data Analyst

• Designed Crypto Impact Potential Index tracking multiple sustainability-focused tokens, performing quantitative evaluation and trend analysis using financial modeling and Python, enabling informed reporting for stakeholders in systemic social innovation ventures.

• Modeled medicinal-foods calming-effect hypotheses with survey and nutritional datasets, applying statistical analysis and visualization to assess stress-sleep-anxiety relationships and support service-learning interventions for mental health initiatives.

• Built zero-subsidy affordable housing financial model using demographic and cost datasets, integrating SQL and Excel to forecast homelessness mitigation potential in dense coastal urban zones, aiding anti-poverty decision-making frameworks.

• Developed behavioral impact dashboard for biophilia initiatives quantifying nature’s stress reduction using proxy data and visual analytics tools delivering actionable insights for facility design teams and wellbeing stakeholders.

• Project: Crypto Impact Potential Index Crafted quantitative analysis for sustainability-oriented crypto tokens, applying Python and financial models to generate impact assessment reports guiding social-innovation investment. Illinois Institute of Technology, IL, USA Aug 2023 – Dec 2024 Data Analyst

• Supported 150+ students with advanced guidance in Applied Statistics and Time Series, providing assistance on statistical modeling assignments, improving student comprehension, and ensuring academic success across multiple courses.

• Mentored 100+ students in Python programming, machine learning workflows, and visualization techniques, enabling hands-on application of analytics for complex coursework and research projects.

• Supervised 10+ teaching assistants, delivering training, facilitating labs, and coordinating grading processes, which streamlined operations and improved the teaching quality across the Computer Science department.

• Delivered course demonstrations and academic workshops on predictive analytics, enabling students to better understand applications of machine learning and statistical methods in solving real-world problems.

• Project: Time Series Forecasting in Applied Statistics Guided student research using Python-based forecasting models, improving reproducibility and academic output.

Isgec Hitachi Zosen Ltd, IN Jun 2019 – Nov 2022

Data Analyst

• Analyzed operational datasets using SQL and Python, identifying bottlenecks that boosted process efficiency by 25% and improved productivity across manufacturing workflows.

• Designed and maintained Power BI dashboards visualizing key production KPIs, enabling department heads to make informed, real-time decisions for process optimization.

• Created predictive models in Python to forecast demand for engineering products, reducing inventory costs by 20% while maintaining supply chain reliability.

• Built and managed ETL pipelines to unify HR, operations, and supply chain data, ensuring clean inputs and consistent compliance reporting.

• Project: Coke Drum Production Analytics Applied SQL and Python to analyze fabrication metrics, detecting cycle-time variances and yield trends, which improved throughput and delivery reliability. EDUCATION

Master in Data Science Dec 2024

Illinois Institute of Technology, Chicago, IL

CERTIFICATION

Microsoft Certified: Power BI Data Analyst Associate (PL-300) PROJECTS

Predictive Analytics for Student Retention & At-Risk Detection (Jun 2024 – Jul 2024)

• Built predictive system with advanced EDA, SMOTE balancing, and Time Series Forest meta-models, achieving 90.9% recall, 96.3% AUC, reducing false negatives by 30% effectively.

• Delivered 10+ visual narratives with interpretable insights to academic teams, improving dropout detection accuracy by 18% and informing targeted support strategies, ensuring optimized resource allocation for better student outcomes. Operational Analytics Platform – Fleet & Logistics Management (Jan 2024 – May 2024)

• Designed normalized MySQL database integrating automated validation and authored 20+ optimized SQL queries, stored procedures, and triggers, ensuring logistics workflows streamlined, reporting automated, and overall data integrity fully maintained.

• Developed OLAP-driven Power BI dashboards tracking 15+ logistics KPIs including fuel efficiency, trip frequency, and maintenance costs, enabling real-time performance monitoring and supporting improved decision-making across fleet operations. Transit System Analytics: Geospatial & Ridership Insights (May 2023 – Jul 2023)

• Processed and modeled 1.2M+ CTA ridership records using regression analysis and API integration, improving scheduling accuracy by 15%, identifying seasonal ridership patterns, and enhancing system efficiency comprehensively overall.

• Delivered 15+ geospatial visualizations with R Leaflet, Matplotlib, and Seaborn, highlighting high-traffic routes, congestion periods, and ridership behavior trends, enabling stakeholders to make data-driven transit planning decisions effectively.

Contact this candidate