Data Analyst Power Bi

Santhi Swarup Yalapalli

LinkedIn • *********************@*****.*** • +1-475-***-****

Summary

Data Analyst with 3+ years of experience in analytics, intelligence, and predictive modeling across healthcare, insurance, and digital domains. Skilled in Python, SQL, Spark, Tableau, Power BI, and Snowflake to deliver insights and automate ETL workflows. Proven track record of driving cost savings, risk mitigation, and customer engagement improvements through robust data pipelines, statistical analysis, and stakeholder collaboration in Agile environments. Education

University of New Haven, West Haven, CT, USA Aug 2023 - May 2025 M.S. in Data Science

IIIT Dharwad, Karnataka, India Aug 2018 - Aug 2022 B.Tech in Electronics and Communication Engineering Certifications: AWS Certified Data Engineer – Associate, Microsoft Certified: Azure Fundamentals Skills

• Programming & Analysis: Python (Pandas, NumPy, Scikit-learn, Statsmodels, Plotly), R, VBA, Regex, APIs

• SQL & Data Warehousing: Complex Joins, CTEs, Indexing, Explain Plan, Snowflake, Redshift, PostgreSQL, SQL Server, BigQuery, Delta Lake, Synapse, dbt (dbt Cloud)

• Visualization & BI: Tableau (LOD, Parameters, Blending), Power BI (DAX, Drillthrough, Row-Level Security), Looker (LookML), Qlik, Excel (PivotTables, Solver, Macros), Google Data Studio, Streamlit, Alteryx

• Data Engineering & Orchestration: PySpark, Databricks, AWS Glue, Talend, Apache Airflow, Kafka, Docker, Jenkins, Terraform, Data Lake Partitioning, Data lake

• Statistics & ML: Logistic/Linear Regression, Clustering (K-means, DBSCAN), Isolation Forest, LightGBM, Time- Series (ARIMA, ETS), Hypothesis Testing, A/B Testing, Feature Scaling, PCA, SHAP Interpretability, MLflow, SageMaker, Feast

• Data Quality & Governance: Collibra, Alation, Great Expectations, Validation Scripts, Anomaly Detection, Data Cataloging, Controlled Access, GDPR & HIPAA Tagging, OAuth2, RBAC

• Project & Delivery: Agile, Scrum, JIRA, Confluence, Storyboards, BRDs, FRDs, UAT, Stakeholder Workshops

• Marketing & CRM Analytics: Google Analytics, Salesforce, HubSpot integration Experience

Discover Financial Services - USA Oct 2024 - Current Data Analyst

• Designed and maintained robust ELT workflows by integrating dbt Cloud transformations on Snowflake with SQL Server data marts, processing large datasets to support weekly dashboards that improved visibility into business performance across product lines.

• Developed advanced LightGBM churn prediction models tracked via MLflow, automating daily scoring jobs that fed into Looker dashboards, enabling marketing teams to adjust business strategies in near real-time and reduce churn by 12%.

• Conducted detailed ad-hoc data analysis on cohort retention trends using Python and PostgreSQL, providing recommendations that directly informed pricing experiments and customer segmentation.

• Automated critical month-end close processes by building Excel VBA scripting tools with Power Query and Solver, shortening financial reconciliation from 5 days to under 48 hours.

• Partnered with cross-functional teams in marketing, finance, and IT to define key performance indicators

(KPIs), embedding them into LookML models that standardized metrics across executive reports.

• Implemented Great Expectations validation scripts across Snowflake staging tables, proactively flagging anomalies and enhancing trust in core reporting solutions by 40%.

• Documented data lineage, glossary definitions, and transformation logic in Confluence, while managing Agile sprints and backlog priorities in JIRA, achieving a 95% on-time delivery rate for analytics initiatives. Deloitte - India Jan 2022 - Aug 2023

Data Analyst

• Engineered end-to-end ingestion and transformation pipelines with Talend, Kafka Streams, and PySpark, loading multi-format datasets into Snowflake to support actuarial models for payer business strategies.

• Designed Tableau dashboards using LODs, bullet charts, and parameter controls to track readmission KPIs, enabling client teams to monitor business performance and optimize care management programs.

• Developed robust A/B testing frameworks in Python (Statsmodels, SciPy) and R, conducting power analyses and hypothesis tests on telehealth engagement campaigns that improved ROI by 20%.

• Implemented orchestration with Apache Airflow, automating Snowflake ELT jobs and downstream Tableau extract refreshes, cutting manual handoffs by 80% and ensuring timely reporting solutions.

• Managed Alation data catalog, tagging PHI/PII columns for GDPR & HIPAA compliance, improving data traceability and reducing audit turnaround times by 50%.

• Collaborated with cross-functional stakeholders including compliance, actuarial, and operations teams to design robust data collection methodologies, supporting scalable analytics workflows.

• Automated actuarial Excel models with ODBC live Snowflake pulls, empowering teams to perform ad-hoc data analysis without waiting on IT extracts, which reduced cycle times by 2 weeks.

• Coordinated JIRA sprints and authored BRDs & FRDs that documented acceptance criteria for new data pipelines, aligning delivery to regulatory audit schedules. Delta Air Lines - India Jan 2021 - Dec 2021

Data Analyst

• Developed scalable ETL frameworks using PySpark on Databricks, transforming nested JSON healthcare claims into Redshift tables, reducing manual data prep by 45% and enabling deeper datasets for fraud analytics.

• Built interactive Streamlit and Plotly dashboards for risk analysts to visualize suspicious provider clusters identified by DBSCAN and Isolation Forest models, improving fraud investigation throughput by 30%.

• Managed containerized microservices with Docker and Jenkins, orchestrating modular enrichment jobs that supported nightly financial reporting solutions with 99% uptime.

• Consolidated disparate operational data sources using Azure Synapse Pipelines, enabling financial teams to run complex Power BI DAX reports on Synapse SQL pools and uncover cost savings opportunities.

• Conducted ad-hoc data analysis in PostgreSQL with advanced window functions (LAG, LEAD, RANK) to model multi-year cohort churn, directly influencing contract pricing and revenue forecasts.

• Automated Excel-based reconciliation templates using VBA macros linked to Snowflake ODBC connectors, empowering finance teams to perform rapid what-if scenario analyses on business performance metrics.

• Authored detailed runbooks and JIRA user stories, facilitating multi-department UAT workshops that validated pipeline outputs against actuarial reserves and strengthened trust across cross-functional teams.

• Participated in Agile ceremonies, analyzed sprint burndown trends via Jira dashboards, and introduced backlog grooming processes that improved sprint predictability by 45%.

Contact this candidate