Stroke Risk Prediction Using Ensemble Learning and Patient Data Analysis
→
Summary
Developed a stacked ensemble model (Random Forest, SVM) for predicting stroke risk from patient data.
Highly analytical Business Analytics professional with a Master's degree and hands-on experience in predictive modeling, AI-driven automation, and cross-functional data strategy. Proven ability to translate complex data into actionable insights, having reduced procurement efficiency by 25% and enhanced search accuracy by 30% through advanced ML and NLP techniques. Skilled in Python, SQL, Power BI, and Agile methodologies, driving data-driven decision-making and delivering significant operational improvements.
Business Analyst Intern
US
→
Summary
Drove operational efficiency and data-driven decision-making by developing analytical tools and optimizing processes for procurement analytics.
Highlights
Developed a Python-based vendor recommendation engine integrated with Power BI, reducing product-related issues by 40% across 500+ items.
Optimized XGBoost-based vendor scoring logic, enhancing end-to-end procurement cycle efficiency by 25%.
Designed and implemented a Power BI dashboard for 15+ teams, streamlining procurement processes and improving task efficiency by 30% through KPI prioritization.
Optimized multi-table SQL queries, including CTEs and window functions, processing over 3 million records to enhance procurement analytics capabilities.
Orchestrated ETL pipelines utilizing Azure Data Factory and Azure APIs to seamlessly ingest procurement data into Power BI datasets.
Data Analyst Intern at UTA Libraries
Arlington, Texas, US
→
Summary
Enhanced data extraction, recommendation systems, and team productivity through advanced analytics and project leadership.
Highlights
Automated research data extraction through 15+ complex SQL queries, accelerating project timelines by 40%.
Enhanced book recommendation precision by 25% using NLP-based semantic search (TF-IDF + cosine similarity) and fine-tuned transformer embeddings.
Led sprint planning and backlog grooming for a 4-member analytics team, improving delivery predictability by 20%.
Data Analyst
Hyderabad, Telangana, India
→
Summary
Improved data consistency, reporting efficiency, and strategic operations through SQL development, BI dashboard creation, and predictive modeling.
Highlights
Developed and optimized SQL scripts for ETL processes, ensuring data consistency and accuracy for large datasets in European transportation projects.
Created Power BI dashboards to visualize supply chain KPIs and performance metrics, enhancing reporting efficiency across multiple departments and reducing manual procurement analysis effort by 30%.
Led predictive modeling projects that informed strategic operations, resulting in a 15% increase in inventory turnover.
→
Masters
Business Analytics with Data Science Concentration
Courses
Python Programming
Cloud Computing
Data Mining
Data Science
Data Warehousing & Business Intelligence
Economic Forecasting
Evidence-Based Management
Capstone Project
Awarded By
The University of Texas at Arlington (UTA)
Awarded for exceptional performance and dedication as a student employee.
Awarded By
Google Developer Groups
Received for exceptional performance.
Awarded By
Cyient
Recognized for outstanding contributions to project success.
Issued By
JPMorgan Chase & Co.
Issued By
UC, Davis
Python, SQL, R, SAS, HTML, CSS.
Tableau, Microsoft Power BI, MS Excel, SAS Enterprise Miner.
Regression, Vertex AI, Vector-Search, Spanner, Random Forest, Classification Models, NLP, XGBoost, TF-IDF, Cosine Similarity, Transformer Embeddings, Ensemble Learning, SVM.
AWS, Database Management, Azure API, Azure Data Factory (ADF), ETL, ELT.
→
Summary
Developed a stacked ensemble model (Random Forest, SVM) for predicting stroke risk from patient data.
→
Summary
Spearheaded a machine learning initiative to analyze over 5,000 Netflix titles using random forest algorithms.