Professional Summary
Hello! I'm Sri Vasudev, a Business and Technology Consultant, Data and Analytics Engineer, and MS candidate in Information Systems at Pace University (Seidenberg School of CS and IS), concentrating in Data Science Engineering and Analytics with a 3.8 GPA.
I bring 2+ years of professional experience spanning Ernst and Young's Business Consulting practice, the Metropolitan Transportation Authority (MTA), and Consilio LLC, delivering data engineering, product analytics, BI reporting, and digital transformation solutions for Fortune 500 clients across automotive, FMCG, energy, and public transit. At EY, I orchestrated 20+ ETL pipelines, deployed executive-level Power BI dashboards, and contributed to AI-enabled cloud platforms under EY ASTERISK that cut time-to-market by 20%. At the MTA, I built analytics ecosystems on Azure Data Lake and enhanced GIS data pipelines supporting enterprise asset management strategy.
I'm AWS Solutions Architect Associate certified and a McKinsey Forward Program alumnus. My technical toolkit spans Python, SQL, Azure, AWS, Power BI, Tableau, Airflow, Docker, and Snowflake, and I work comfortably across data engineering, business intelligence, solutions architecture, consulting strategy, and product analytics. I'm currently seeking 2026 full-time opportunities in Data Engineering, Analytics, Product, Strategy, and Technology Consulting.
Core Competencies
Professional Experience
For complete work history refer to my curriculum vitae.
Data Strategy Analyst - EAM, Strategic Initiatives
- Built analytics ecosystem on Azure Data Lake, deploying production-grade Power BI dashboards with KPI frameworks and GIS, translating complex datasets into self-service analytics that improved decision-making accuracy by 20%+.
- Optimized GIS analytical pipelines on Azure within HxGN EAM, improving data quality and enabling real-time operational dashboards for enterprise asset management.
- Conducted cohort-level benchmarking across operational datasets, driving a 15% improvement in system efficiency while streamlining project governance using Jira & Confluence.
Advanced Analyst, Staff II - Business Consulting, Analytics & Strategy
- Spearheaded the EY ASTERISK SaaS platform's digital transformation, crafting product roadmaps and GTM strategies for AI-enabled SCM solutions.
- Orchestrated 45+ high-performance ETL data pipelines (Python, SQL, Azure Databricks) powering analytics for Fortune 500 clients, improving data accuracy by 30%.
- Deployed 10+ Power BI dashboards integrating KPIs and Geo-based vendor data, driving a 35% boost in operational efficiency.
- Drove CRM integration and customer experience analytics, partnering with C-suite stakeholders and streamlining end-to-end product strategy.
Data Operations Analyst
- Designed & implemented cloud-based data pipelines for legal eDiscovery forensics, enforcing data privacy compliance across 5,000+ legal records.
- Built data warehousing solutions and automated analytics workflows, improving pipeline efficiency by 20% and analytical output by 30%.
Education
MS, Computer & Information Systems
Data Science Engineering & Analytics | GPA: 3.8
BS, Computer Science
Applied CS, Cloud, Data & Analytics | GPA: 3.64
Projects, Research & Certifications
Certifications
Publications
Academic Research
-
"THE SUGGESTIVE BANKER"
Capstone: Consumer Trust in Agentic AI for Digital Banking · 2026
Projects
SmartChurn – Credit Card Attrition Prediction System
Mar 2025 – Present
Show details
- Conducted end-to-end development of a customer churn prediction system for Great One Bank using a 10K-record dataset, integrating Tableau-driven EDA and Python-based machine learning.
- Performed statistical and visual analysis in Tableau to assess the impact of credit limits and other features on churn behavior; confirmed credit limit as a statistically significant factor via t-tests (p < 0.05).
- Built and validated a high-performance CatBoost classification model, achieving 97.17% accuracy, 90.77% precision, and 92.48% recall, outperforming baseline models like Logistic Regression and Random Forest.
- Addressed class imbalance (266 attrited vs. 1324 existing) using SMOTE and hyperparameter tuning (auto_class_weights = 'Balanced') to optimize recall and reduce false positives.
- Final production test (Phase 3) underway: applying trained CatBoost model to an unseen "live" batch of 100,000+ customers, ensuring 20/80 attrition-to-retention ratio adherence for real-world deployment accuracy.
HeartBeacon – Cardiovascular Disease Prediction Model
Nov 2024 – Dec 2024
Show details
- Engineered a heart disease prediction pipeline using Python and a 319,000+ record dataset from Kaggle, achieving 90% accuracy through robust preprocessing, outlier treatment, and data balancing techniques (SMOTE, Tomek Links, NearMiss).
- Built and evaluated classification models including Logistic Regression, Decision Tree, and Random Forest; optimized for recall in minority class (heart disease presence) using random over-sampling.
- Implemented EDA and data visualization using Seaborn and Matplotlib, uncovering key clinical insights like the impact of BMI, sleep time, and mental health on heart disease.
- Spearheaded standardization, categorical encoding, and exploratory data analysis to create a cleaned and normalized dataset for scalable healthcare modeling.
- Hosted project on GitHub with detailed notebooks and reproducible codebase for future research and model improvement.
Let's Connect
I am actively seeking 2026 full-time opportunities in Data, Product, and Tech Strategy. Feel free to reach out!