Machine Learning Senior Analyst

Ramya Rani Raya

Senior Analyst

*************@*****.***

https://www.linkedin.com/in/ramyaraniraya

+1-945-***-****

Dallas, TX, USA

●Highly accomplished Senior Analyst with 4+ years of experience in Data Engineering, Business Intelligence and Machine Learning, specializing in SQL optimization, ETL development, cloud computing and data visualization.

●Proficient in advanced machine learning techniques including Random Forest, Bayesian inference, NLP and Time Series Analysis using TensorFlow and PyTorch.

●Experience in building interactive dashboards and reports using Power BI, Tableau and Excel improving data accessibility and business insights.

●Proficient in data manipulation and statistical modeling with Python libraries such as Pandas, NumPy, and Scikit learn, facilitating in-depth predictive analytics and data insights.

●Integrated Python with big data technologies like Apache Spark and cloud platforms including AWS and Google Cloud, optimizing data processing and scalability.

●Utilized Amazon Web Services (AWS) for cloud-based data storage, processing, and analytics, gaining foundational expertise in AWS S3 for secure data storage and retrieval.

●Leveraged AWS Redshift for scalable data warehousing, enhancing querying capabilities and supporting extensive data analysis projects with high-performance processing.

●Managed application hosting and database solutions using AWS EC2 instances and RDS, optimizing system performance and ensuring robust data management.

●Implemented system monitoring and troubleshooting with AWS CloudWatch, collaborating with teams to utilize AWS's pay-as-you-go model for cost-effective cloud solutions.

●Proficient in advanced Excel functions like VLOOKUP, INDEX-MATCH, PivotTables, and macros to enhance data analysis, reporting, and streamline workflows.

●Automated recurring tasks using VBA scripts in Excel, improving productivity by 30% and enhancing data management efficiency.

●Created dynamic dashboards and reports in Excel to track KPIs and support decision-making for senior management, facilitating real-time business insights.

●Experienced in handling large datasets and performing complex calculations using Power Pivot, optimizing data analysis and business intelligence.

●Skilled in data cleaning, validation, and formatting with Excel, ensuring accuracy and consistency in reporting and analysis.

●Proficient in using IBM SPSS to clean, preprocess, and transform raw data into structured datasets by handling missing values, outliers, and ensuring data accuracy.

●Integrated the adoption of Apache Spark to handle large-scale data processing, reducing the time required for complex data analysis tasks by 40%.

●Optimized machine learning workflows using Databricks, significantly reducing the model training cycle and enhancing the efficiency of deploying machine learning models.

●Developed predictive models using TensorFlow, enhancing strategic decision-making by improving data-driven strategies across various business units.

●Implemented Bayesian statistical models to enhance decision-making processes, especially in areas of risk assessment and product development, improving overall business resilience and adaptability. Visualized data trends using advanced techniques in Tableau and Power BI, enhancing understanding and decision-making capabilities by clearly presenting market and operational insights.

●Led Testing and Automation code work, implementing best practices in continuous integration and continuous deployment (CI/CD) environments, which reduced bug rates and deployment times. Implemented natural language processing (NLP) techniques to analyze and interpret customer feedback, resulting in a 15% increase in customer satisfaction and better alignment of product offerings with customer needs.

●Led initiatives to optimize ETL pipelines, reducing data processing times by over 40% and significantly enhancing the timeliness and reliability of data for business operations.

●Integrated Excel with other tools like SQL and Tableau, creating comprehensive analytics workflows that enhance data accessibility and insight generation.

●Developed cross-platform applications in C++ using Qt and other frameworks, ensuring compatibility across Windows, Linux, and macOS.

●Implemented multithreading in Java to improve the efficiency and responsiveness of real-time applications, reducing processing time by 25%.

●Developed embedded systems for microcontrollers using C, achieving high performance with constrained resources.

Work Experience

Senior Analyst Jan 2024 - Present

Optum UHG Minneapolis

●Designed Type 1 and Type 2-dimension tables, developing strong data models to accommodate both current and historical data requirements effectively.

●Created procedures to unload data from Snowflake to internal stages, optimizing data storage and access.

●Developed automated Excel dashboards using PivotTables, Power Query and VBA to streamline data analysis.

●Optimized SQL based ETL pipelines in snowflake and Microsoft SQL server to improve data processing.

●Automated data validation and transformation using Talend Open Studio for efficient data management.

●Developed and optimized data pipelines utilizing AWS Lambda, Python, Cradle, and Redshift, automating data collection, processing, and analysis.

●Integrated AWS Glue, Athena, Kafka, Spark EMR, and Step Functions to enhance the automation and efficiency of data pipelines.

●Improved data processing efficiency, addressing tasks like ingestion, transformation, deduplication, and S3 storage reclamation.

●Tableau’s advanced analytics capabilities to create predictive models for patient readmission risks, enhancing patient outcomes through proactive management.

●Utilized Tableau Desktop to create visually appealing views, dashboards, and reports, ensuring data validation for correctness and integrity.

●Automated data refresh operations on Tableau Server, maintaining up to date insights for business use.

●Managed Redshift databases and resources using AWS CDK, ensuring data consistency and accuracy across all stages of the pipeline.

●Utilized IBM SPSS to perform data analysis and statistical modeling, including descriptive statistics, regression analysis, and hypothesis testing, to support data-driven decision-making.

●Created dynamic visualizations such as charts, graphs, and tables in SPSS to effectively communicate data insights to stakeholders and support presentations.

●Conducted advanced multivariate analyses e.g., factor analysis, cluster analysis in SPSS to identify key patterns, relationships, and trends within large datasets.

●Automated the deletion of orphan objects using AWS Lambda, Java, and TypeScript, significantly reducing storage costs and improving efficiency.

●Collaborated closely with application developers and administrators to enhance data flows between internal and external systems and Snowflake.

●Established data pipelines to Snowflake from various sources, streamlining data integration and accessibility.

●Transformed data during load to internal and external stages, enhancing data processing and utilization.

●Created and optimized complex SQL queries for extracting, modifying, and analyzing large datasets, driving actionable insights for strategic decision-making.

●Designed S2T mapping for MLD and Retro MLD, facilitating the loading of HEDIS Measures through canonical documentation.

●Handled the loading of measures and flagged events with Snowpipe, improving real-time data handling and responsiveness.

●Created user stories in Rally, enhancing project documentation and tracking for agile development processes.

●Conducted refinement and retrospective sessions after every sprint, improving team practices and sprint outcomes through structured feedback.

●Streamlined data validation procedures to assure the correctness and integrity of data used in business intelligence and analytics.

●Utilized AWS Lambda for automating tasks within data management workflows, enhancing operational efficiency.

●Developed visualizations and dashboards in Tableau, providing key business insights and supporting strategic decision-making processes.

●Managed and optimized AWS Redshift resources, ensuring efficient data storage and quick access for analytics purposes.

●Implemented data quality checks and balances using Python scripts to ensure the accuracy and reliability of the data pipeline.

●Enhanced data warehousing practices with Snowflake, leveraging cloud scalability and performance to support data-driven decision-making.

●Optimized the management of database schemas, tables, views, and stored procedures in Redshift, maintaining high standards of data governance.

●Optimized C code for time-critical applications, improving execution speed by 20% and ensuring compliance with strict timing constraints.

●Created RESTful APIs in Java to support microservices architecture, ensuring seamless integration with frontend applications.

●Worked with C Standard Library to utilize containers, algorithms, and iterators to build high-performance applications with minimal overhead.

●Designed and deployed a PHP based customer portal with MySQL for improved user experience.

●Created interactive dashboards in Power BI and Tableau to support data driven decision making.

Environment: Python, Excel, Databricks, Snowflake, Redshift, AWS, SQL, Tableau, Hive, NLP, ML Models (Random Forest,), Bayesian Inference.

Business intelligence engineer May 2019 - Jun 2022

Capgemini Bengaluru

●Developed various data connections and designed comprehensive Power BI reports and dashboards, enhancing data visualization and user engagement.

●Automated monthly performance reports in Power BI, delivering timely insights to authorized users and saving significant manual effort.

●Created standardized Word templates for technical Documentation and reporting.

●Designed PowerPoint presentations incorporating visuals and data insights for executive meetings.

●Built Java based microservices integrating XML/JSON APIs for seamless data exchange.

●Developed complex SQL queries for data warehousing and analysis, achieving a 40% improvement in data retrieval efficiency.

●Conducted rigorous SQL-based testing to validate data accuracy and integrity, ensuring reliability and trustworthiness of the information provided.

●Utilized SQL queries to streamline data extraction and loading processes, enhancing the speed and accuracy of data retrieval.

●Leveraged Python-MYSQL Connector and MYSQL DB package to seamlessly query MYSQL databases from Python, improving performance and scalability.

●Analysed and developed key performance indicators (KPIs) through automated reporting in Power BI and Excel, facilitating enhanced decision-making and strategic planning.

●Developed automated processes for operational workflows in Power BI, optimizing key metric reporting to reinforce decision-making models.

●Created a real-time Power BI dashboard, reducing manual reporting by 10 hours per week and providing effortless KPI analysis.

●Integrated ETL operations into Power BI dashboards, enhancing data processing precision and accessibility, and reducing manual data handling.

●Utilized AWS Lambda to automate the elimination of orphan objects, employing Java and TypeScript to streamline processes, which resulted in considerable storage cost savings and increased efficiency.

●Designed and implemented SQL queries for advanced data modeling and analytics, extracting actionable insights from complex datasets.

●Automated data integrity checks and cleanup processes, using SQL and Python to maintain high data quality standards across platforms.

●Developed and maintained scalable ETL pipelines using Python, ensuring efficient data flow and transformation for real-time analytics.

●Optimized database schemas and SQL queries for performance, significantly enhancing response times and user experience in Power BI dashboards.

●Implemented robust data security protocols within SQL databases, safeguarding sensitive information against unauthorized access and breaches.

●Conducted in-depth data analysis to identify trends and patterns, using Power BI to translate findings into strategic business insights.

●Developed automated alerting and monitoring systems in Power BI, enabling proactive management of business operations and immediate response to critical changes.

●Enhanced data extraction techniques using advanced SQL programming, enabling more sophisticated data manipulation and faster insights generation in Power BI.

●Pioneered the adoption of machine learning algorithms in Power BI reports, integrating predictive analytics to forecast trends and inform business strategies.

●Conducted training sessions on Power BI and SQL best practices, enhancing team capabilities and ensuring effective use of business intelligence tools.

●Optimized data warehouse performance using Redshift, implementing best practices for data storage and query optimization to support extensive analytics platforms.

●Automated routine data management tasks using Python scripts, reducing the need for manual intervention and increasing operational efficiency.

●Developed a comprehensive backup and recovery strategy for SQL databases, ensuring data availability and continuity in case of system failures.

Environment: SQL, Power BI, excel, Tableau, ETL, SharePoint, AWS, Python.

Core Skills

Programming Languages & Frameworks: Python, SQL, VBN, JavaScript.

Database Technologies & Data Management: MYSQL, PostgreSQL, SQL Server, AWS Redshift. Snowflake, Apache Hive, AWS, Apache Airflow, AWS Glue, Apache Kafka, Encryption, Access Control, Compliance.

Data Visualization & Reporting Tools: Power BI, Tableau, Excel.

Machine Learning & Predictive Analytics: TensorFlow, PyTorch, Random Forest, Bayesian Inference, Time Series Analysis, Forecasting Models, NLP.

Big Data & Cloud Computing: Apache Spark, AWS EMR, AWS, GCP.

Additional Tools: Databricks (Machine Learning Optimization), Jupyter Notebooks (Data Science & Analysis), SharePoint (Documentation & Collaboration).

Education

University of North Texas Aug 2022 - May 2024

Master of Science Data Analytics

Osmania University June 2016 - May 2019

Bachelor of Science Computer Science

Contact this candidate