SAI AKHIL SADULA

Designed interactive Power BI dashboards to track provider performance and claims status, reducing reporting time by 6 hours/week.

Built predictive models using Scikit-learn and logistic regression to identify high-risk patient populations, supporting targeted care programs for 25,000+ patients.

Automated ETL pipelines with AWS Glue and SQL Server, decreasing manual data handling errors by 40% across clinical data systems.

Implemented HIPAA-compliant data governance protocols, ensuring 95% compliance with PHI data policies and improving audit readiness.

Collaborated with data engineering teams in agile sprints, enhancing backlog delivery velocity by 15% using Jira and Scrum.

Created interactive dashboards in Tableau and Power BI to track student performance metrics, enhancing instructor decision-making and feedback processes.

Developed Python automation scripts to streamline grading workflows, reducing manual effort by 30% through automated data processing.

Leveraged AWS S3 and EC2 services for scalable data storage and computation, ensuring fast and reliable data management for large student datasets.

Generated 120+ SQL-based analytical reports, tracking 10M+ guest bookings and revenue trends across 50+ global markets to inform regional strategy.

Designed and implemented K-Means clustering models on 1.2M user records, enabling personalized campaigns for 600,000+ users.

Built and managed a 15M+ record Snowflake data warehouse, improving query performance for cross-functional dashboards.

Automated 25+ recurring data workflows via Azure Data Factory, reducing manual effort by 80%+ and enhancing pipeline reliability.

Developed interactive Tableau dashboards to monitor refund trends and fraud alerts across 20+ markets, accelerating fraud detection by 75% (from 48 to under 12 hours).

Standardized cleaning of 12 mission-critical datasets using Pandas, eliminating 95% of inconsistent entries and improving model training data integrity.

Developed automated Excel dashboards with pivot tables and macros to deliver weekly summaries on 10,000+ energy usage records, enabling faster executive-level reviews.

Supported ETL pipeline design using SSIS, improving data integration across 3 business units and reducing sync errors in supply chain data by 30%.

Wrote intermediate SQL queries in PostgreSQL to extract monthly KPIs from 12,000+ logistics records, tracking 200+ shipments/month.

Performed data cleaning on 500K+ supply chain rows using Pandas, achieving 95% data quality score as verified by internal audit teams.

Analyzed inventory data spanning 2 fiscal years, uncovering seasonal overstock trends that led to an estimated reduction of 8,000+ excess units across key SKUs.