Sravanthi G

• Collaborated with the model risk management team to identify and mitigate AML-related risks through the application of robust risk models.
• Built and tested logistic regression models on historical AML data to detect unusual transaction patterns and improve compliance reporting.
• Created comprehensive model documentation and presented insights to senior management and non-technical stakeholders, simplifying complex concepts for business decision-making.
• Designed visual dashboards and data summaries using matplotlib to highlight model results and fraud detection KPIs.
• Ensured alignment of model development with regulatory guidelines and governance frameworks, enhancing audit readiness.

Environment: Python, Pandas, NumPy, Scikit-learn, Matplotlib, AWS S3

• Developed a logistic regression model to identify suspicious accounts (SAR), improving fraud detection accuracy and reducing potential financial risks.
• Extracted and processed large AML datasets from AWS S3 using Python, ensuring efficient data integration for modeling.
• Conducted feature engineering and variable analysis to identify significant predictors, enhancing overall model performance.
• Evaluated model efficiency using Precision, Recall, and F1-score, ensuring balanced predictions while minimizing false positives and negatives.
• Utilized Python libraries such as pandas, NumPy, scikit-learn, and matplotlib for data manipulation, visualization, and predictive modeling.

Environment: Python, AWS S3, Pandas, NumPy, Scikit-learn, Matplotlib, SQL

• Designed and developed data integration pipelines using Informatica IICS Data Integration (DI) to extract, transform, and load data from on-premises and cloud sources into Snowflake and Azure SQL Data Warehouse.
• Configured and optimized IICS mappings, tasks, and taskflows to enable seamless data movement across multiple systems, reducing manual intervention and improving ETL efficiency.
• Integrated REST and SOAP APIs within IICS workflows for real-time data ingestion from third-party applications and cloud platforms, enhancing data availability for reporting.
• Collaborated with teams to build parameterized mappings and implement dynamic connections in IICS for multi-environment deployments, improving reusability and reducing maintenance overhead.
• Implemented error handling, notifications, and logging mechanisms within IICS taskflows to ensure better monitoring and troubleshooting of integration processes.
• Worked closely with Azure Data Factory, Snowflake, and SQL Server to support hybrid-cloud ETL solutions, ensuring scalable data pipelines for analytics and business intelligence reporting.

Environment: Informatica IICS DI, REST & SOAP APIs, Azure Data Factory, Snowflake, Azure SQL Server, Python, Unix Shell, Agile/Scrum, Control-M

• Designed and developed complex ETL workflows in Informatica PowerCenter to extract, transform, and load data from Oracle, Teradata, DB2, and SQL Server into enterprise data warehouses for analytics and reporting.
• Optimized ETL performance by tuning SQL queries, leveraging pushdown optimization, and fine-tuning PowerCenter sessions, workflows, and cache sizes, achieving up to 40% reduction in execution time.
• Administered Informatica PowerCenter repositories and servers, including user management, repository backups, environment migration, and production support, ensuring high-availability ETL operations.
• Integrated Unix Shell scripts, Python scripts, and scheduler tools like Control-M to automate PowerCenter workflows and improve data pipeline reliability.
• Collaborated with stakeholders during the cloud migration phase, preparing existing on-premises PowerCenter mappings for transition to Informatica IICS, Snowflake, and Azure Data Factory, ensuring a smooth hybrid-cloud data integration strategy.
• Performed end-to-end data lineage and impact analysis using Informatica Metadata Manager, ensuring data governance, compliance, and smooth integration with modern cloud-based IICS pipelines.

Environment: Informatica PowerCenter, Informatica Data Quality (IDQ),Oracle, Teradata, DB2, SQL Server, Snowflake, Azure SQL Data Warehouse, Unix Shell (Bash/Korn), Python, Control-M, Azure Data Factory, Repository Administration, Agile/Scrum