Data Analyst Azure

Sowmya Nomula

940-***-**** **************@*****.*** https://www.linkedin.com/in/sowmyanomula/

Objective

Entry-Level Analyst passionate about leveraging data for actionable insights and decision-making. Skilled in analysis, problem-solving, and visualization.

Skills

Programming: Python, R (certified), SQL

Data Science Tools: TensorFlow, PyTorch, Scikit-learn, XGBoost, AWS SageMaker Data Visualization: Tableau, Power BI, Excel, Matplotlib, Seaborn Big Data: Hadoop, Spark, Hive, HDFS, PySpark, AWS Glue Experience

DAIR Aug 2023 - July 2024

Data Analyst/Data Engineer, Intern Denton, USA

• Extracted, cleaned, and processed large datasets from various institutional sources (e.g., student enrollment, academic performance, faculty data) to support research and decision-making.

• Performed complex data analysis in support of ad-hoc and standing customer requests

• Designed and developed automation test scripts using Python.

• Worked with Systems Development Life Cycle (SDLC)/ Software as a Service (SaaS) delivery models.

• Designed and implemented secure data pipelines into a Snowflake data warehouse from on-premise and cloud data sources

• Implemented Data Lake in Azure Blob Storage, Azure Data Lake, Azure Analytics, Data bricks Data load to Azure SQL Data warehouse using Polybase, Azure Data Factory

• Designed and implemented effective Analytics solutions and models with Snowflake.

• Queried and analyzed data from Cassandra for quick searching, sorting and grouping

• Involved in Data profiling, Data analysis, data mapping and Data architecture artifacts design.

• Extensively created data pipelines in cloud using Azure Data Factory.

• Worked with Azure Data Factory (ADF) since its a great SaaS solution to compose and orchestrate Azure data services.

• Wrote python scripts to parse XML documents and load the data in database.

• Used Erwin Data Modeler tool for relational database and dimensional data warehouse designs.

• Designed data pipelines using Azure Data Factory, IBM DataStage / Infosphere, Azure Copy, Polybase, Multi region data replication

• Involved in complete SSIS life cycle in creating SSIS packages, building, deploying and executing the packages all environments.

• Developed MDM integration plan and hub architecture for customers, products and vendors, Designed MDM solution for three domains.

• Written SQL queries against Snowflake.

• Implemented Custom Azure Data Factory pipeline Activities and SCOPE scripts.

• Used DSE SQOOP for importing data from RDBMS to Cassandra

• Developed reports for users in different departments in the organization using SQL Server Reporting Services

(SSRS).

• Developed and supported on Oracle, SQL, PL/SQL and T-SQL queries.

• Developed reports and interactive dashboards using tools like Tableau to provide insights on student success, retention rates, and institutional performance metrics.

• Applied statistical models and machine learning techniques to analyze trends in enrollment, graduation rates, and other key performance indicators to support university planning.

• Ensured data accuracy, consistency, and compliance with institutional policies and regulatory requirements like IPEDS reporting, accreditation metrics.

Accenture May 2022 - Dec 2022

Data Analyst Hyderabad, India

• Led data migration projects from Salesforce CRM to cloud platforms (AWS Redshift, Snowflake, Azure Synapse), ensuring data integrity, security, and compliance (GDPR, SOC 2) using Python, SQL, and API automation.

• Designed and optimized ETL workflows to extract, transform, and load data between Salesforce CRM and cloud data warehouses, improving data integration and processing efficiency.

• Built Python-based automation scripts utilizing REST/SOAP APIs for lead management, customer data synchronization, and sales process automation, integrating Salesforce with BI tools like Tableau, Power BI, and Snowflake for real-time insights.

• Developed dashboards and reports using Tableau, Power BI, and Excel to highlight key trends, enhance decision- making, and ensure data quality through governance practices like RBAC and audit logs.

• Collaborated with team members to ensure data quality and accuracy in reporting. Academic Projects

Customer Churn Prediction Python, TensorFlow, Tableau, Excel, AWS SageMaker

• Built a predictive churn model using Python, TensorFlow, and AWS SageMaker, leveraging customer behavior data to identify at-risk users across OTT platforms. a machine learning model to predict churn across OTT platforms.

• Engineered key features from streaming data, user demographics, and engagement metrics, improving model accuracy and interpretability.

• Developed an interactive Tableau dashboard to visualize churn insights, enabling business teams to take proactive retention actions.

Capstone Project Humana Mays Case Competition of the Humana Mays project Data Analyst — Health Analytics

• Developed an XGBoost model to identify disengaged LPPO plan members likely to miss preventive PCP visits, aiding healthcare interventions.

• Managed and pre-processed 14 real-time datasets (1.5M+ records) with demographics, claims, and behavioral data for predictive analysis.

• Identified key risk factors like age, rural residency, and poor health indicators driving disengagement in preventive care.

• Recommended targeted outreach, telemedicine, and incentives to enhance member engagement and healthcare outcomes.

Contact this candidate