Lavanya Ramakrishna

Collect, clean, and validate mortgage loan data from various sources, ensuring accuracy and completeness. Perform exploratory data analysis to identify anomalies and/ or errors within the mortgage loan data.    File Mapping and Integration:  Develop and implement file mapping strategies to ensure seamless integration and data compatibility between systems.  Collaborate with cross-functional teams, including IT and software developers, to define data mapping requirements and specifications.  Conduct thorough testing and validation of data mappings to ensure accuracy and data integrity.    Report data errors and anomalies:  Create comprehensive reports and visualizations to present findings and key performance indicators related to residential mortgage loan data.  Identify opportunities for process improvements and automation to enhance data reporting efficiency.    Data Quality Assurance:  Establish data quality standards and protocols to ensure the accuracy, completeness, and consistency of mortgage loan data.  Conduct data validation and quality checks to identify and resolve data discrepancies or inconsistencies.  Collaborate with stakeholders to implement data governance policies and procedures.  Collaboration and Communication:  Collaborate with cross-functional teams, including business analysts, lenders, and underwriters, to understand data requirements and provide analytical support.  Communicate complex data analysis findings and insights effectively to non-technical stakeholders, both verbally and through reports and presentations.  Provide guidance and mentorship to junior analysts, sharing best practices and promoting a data-driven culture.   

• Designed and executed advanced statistical models for credit risk prediction, using machine learning techniques and tools such as Python, resulting in an average improvement of 15% in model accuracy. • Managed data cleansing, validation, and modeling activities, ensuring the quality and accuracy of data used in credit prediction models, reducing data error rates by 20%. • Analyzed large amounts of client data, and identified patterns and trends that informed the development of models, leading to the identification of previously unknown risk factors. • Generated actionable insights and recommendations, based on data analysis and modeling, to support informed credit risk decisions, resulting in a 10% decrease in credit risk exposure. • Demonstrated expertise in data science, machine learning, and the mortgage industry, contributing to the success of the team and organization

• Supporting the core operations teams as IT analyst for a Client Deutsche Bank across globe. • Partnered with Tier II and Tier III help desk peers based across globe to resolve complex Software problems that required escalation. Provided detailed descriptions of issues in trouble ticket system and followed up diligently to ensure swift resolutions. • Educating new joiners with refresher training to provide process knowledge. • Conducting sessions to keep the team up to date about new processes and skills