Shilpa Umredkar

About Me

Shilpa Umredkar has 11 years of experience delivering end-to-end solutions in fraud monitoring, retail banking, and reporting domains. Leveraged Prompt and Copilot tools to significantly boost efficiency and lead the migration of legacy SAS systems to Python, enhancing scalability and performance. Expert in Python automation and cloud-based infrastructure modernization. Skilled in developing automated reporting solutions using data lake environments to optimize processes. Experienced in managing cross-functional teams, driving data quality improvements, and excelling in requirement gathering, stakeholder collaboration, and delivering dependable analytical solutions.

Skills

• Technical: Python, PySpark, NLP, Flask, Django, Machine Learning Algorithms, PyTest, REST API, SQL / MySQL / PostgreSQL / Azure SQL, GCP (BigQuery, Dataproc, Cloud Storage), AWS (Lambda, S3, SNS), GitHub, Copilots, Notebook LLM, Napkin, Open AI, Data Governance, Data Quality, ETL pipelines.
• Domain / Business: Fraud Monitoring, Credit Risk, Retail & Personal Banking, Data Quality & Governance, Stakeholder Communication, Team Leadership, Project Management
• Soft Skills: Leadership, Team Management, Client Communication, Requirement Analysis, Data Mapping & Documentation

My Experience

•Led the migration of complex SAS-based reporting applications to Python and PySpark, achieving enhanced performance and scalability.

•Utilized GitHub Copilot extensively with few-shot and example-based prompting techniques to accelerate code generation and improve development efficiency.

•Developed robust Python/pyspark automation scripts for end-to-end reporting pipelines, reducing manual interventions by 80% and optimizing data integration into Data Lake environments.

•Designed reusable data assets in Data Lake to support scalable and efficient reporting solutions aligned with organizational data democratization goals.

•Collaborated with stakeholders to gather requirements and prepared detailed FRD and BRD documents to guide migration and automation projects.

•Conducted proactive data validation and quality checks using SQL, Python, PySpark, and BigQuery to ensure data integrity during and after migration. Created comprehensive flowcharts and data flow diagrams to enhance understanding of end-to-end data lineage and use cases.

•Created comprehensive documentation for data quality frameworks, governance, and technical workflows supporting credit risk and fraud monitoring initiatives.

•Developed data quality monitoring tools and automated notification systems using Python and PySpark to maintain high data standards post-migration. Defined data mappings and conducted data gap assessments for transformation processes, ensuring completeness and integrity of data from source to target.

EDUCATION & CERTIFICATIONS
Bachelor of Engineering — RTM Nagpur University, 2012

Certifications:

• Applied Data Science (Coursera)
• AWS Fundamentals: Serverless Application Building