NAGA SAI DHANYA VEEREPALLI
Fairfax,United States
Summary
Data Analyst / Data Scientist with 4+ years of experience applying SQL, Python, machine learning, causal inference, and cloud analytics to solve business problems across marketing, real estate, and consumer marketplace domains. Proven ability to build predictive models, run large-scale experiments, automate data pipelines, and deliver executive-ready dashboards using Tableau, Power BI, and Looker. Skilled at translating ambiguous questions into measurable analytics and collaborating with cross-functional teams to improve performance, optimize spend, and unlock ROI. Strong background in AWS, PySpark, experimentation, and scalable ML solutions.
Overview
5
5
years of professional experience
Work History
Data Scientist – Marketing & Growth Analytics
Archon Software LLC
04.2025 - Current
- Interrogated 5M+ consumer interaction records using SQL and Python to surface behavioral patterns, boosting retargeting efficiency by 19%.
- Architected predictive models (regression, classification, uplift) in scikit-learn to pinpoint high-value audiences, elevating campaign ROI by 24%.
- Validated A/B and multivariate experiments, strengthening statistical confidence for budget decisions by 30%.
- Composed Tableau/Power BI/Looker dashboards that enabled leadership to track KPIs (CPL, CAC, LTV) in real time.
- Engineered PySpark workflows across AWS S3, EMR, and Glue, accelerating data refresh cycles from 6 hours to 45 minutes.
- Transacted complex business problems, applying measurable analytical frameworks, driving a 12% gain in lead-to-close conversion rates.
- Tech Stack: SQL (Python, pandas, numpy, scikit-learn) | PySpark | AWS (S3, EMR, Glue) | Tableau | Power BI | Looker | Experimentation & Causal Inference
Data Scientist – Advanced Analytics & Experimentation
Cognizant Technology Solutions
06.2021 - 12.2022
- Investigated 100K+ engagement logs using Python, SQL, and R to develop predictive models that increased accuracy by 25%, improving targeting decisions across 3 major sectors.
- Programmed churn and risk-scoring pipelines in Dataiku - scikit-learn that identified at-risk users with 85% precision, enabling teams to recover 12% of previously lost accounts.
- Evaluated 20+ A/B and cohort experiments in scikit-learn to optimize marketing techniques, boosting digital program engagement by 15% and informing $500K in annual budget allocations.
- Automated BERT-based and LLM-driven classification workflows that cut manual review time by 50%, enabling analysts to process 100K+ logs/day with zero downtime.
- Prototyped 15+ Tableau/Power BI/Looker dashboards that reduced reporting turnaround by 40% and Updated KPI visibility for 10+ business units.
- Fortified sensitive datasets by configuring AWS VPC and SSH-based access controls, lowering security compliance risks by 35% and meeting enterprise audit requirements.
- Tech Stack: Python | R | SQL | Dataiku | scikit-learn | SPSS | Tableau | Power BI | Looker | BERT | AWS
Junior Data Analyst
Cognizant Technology Solutions
08.2020 - 05.2021
- Consolidated 1M+ multi-source records using PostgreSQL, MySQL, and SparkSQL to accelerate query execution by 30%, improving daily analytics throughput for cross-functional teams.
- Developed 20+ Tableau, Power BI, and Looker dashboards that increased KPI visibility for senior leadership by 54%, supporting data-driven decisions across 5 business units.
- Systematized ETL pipelines using AWS Glue and EMR, reducing reporting delays by 35% and enabling near real-time refreshes for operations and finance teams.
- Generated predictive features in Python and R that boosted churn-model accuracy by 17%, strengthening retention analytics and segmentation workflows.
- Optimized Linux/Shell workflow execution, cutting manual intervention by 28% and increasing reliability of nightly data jobs across 3 environments.
- Validated HTML and Java-based reporting interfaces, improving dashboard stability and usability by 32% through systematic defect detection and UI performance checks.
- Tech Stack: PostgreSQL | MySQL | SparkSQL | Python | R | Tableau | Power BI | Looker | AWS Glue | EMR | Linux | Java
Education
Master Of Science - Data Analytics Engineering
George Mason University
United States12.2024
Skills
- Programming & Querying: SQL (PostgreSQL, MySQL, SparkSQL, T-SQL), Python (pandas, numpy, scikit-learn, scipy, joblib), R, Shell Scripting
- Machine Learning & Statistics: Regression, Classification, Clustering, Causal Inference, Uplift Modeling, Hypothesis Testing, Confidence Intervals, A/B Testing, Cohort Analysis, Time Series Forecasting
- Frameworks & Libraries: scikit-learn, TensorFlow, PyTorch, Dataiku, MLlib
- Data Engineering & Cloud: AWS S3, AWS Glue, AWS EMR, AWS Lambda, AWS Redshift, AWS SageMaker, PySpark, Databricks, Docker, Kubernetes, Dask
- Business Intelligence & Visualization: Tableau, Power BI, Looker, Excel (Power Query, DAX, VBA), QlikView, SAP Analytics, AWS QuickSight
- Tools & Version Control: Git, GitHub, GitLab, CI/CD Pipelines, Unix/Linux
Websites
Timeline
Data Scientist – Marketing & Growth Analytics
Archon Software LLC
04.2025 - Current
Data Scientist – Advanced Analytics & Experimentation
Cognizant Technology Solutions
06.2021 - 12.2022
Junior Data Analyst
Cognizant Technology Solutions
08.2020 - 05.2021
Master Of Science - Data Analytics Engineering
George Mason University