Yogamaya Dash

Analyzed and mitigated risks, achieving a reduction in AML incidents through the implementation of advanced data analytics techniques, including logistic regression and random forest. Utilized machine learning algorithms to enhance fraud detection and prevention measures, resulting in a 25% increase in accuracy. Spearheaded the 'Unbox the Black Box' project, utilizing Python for impact analysis and change tracking. Implemented NLP techniques to analyze textual data and leveraged GCP, PySpark, and Hive for data processing.

Client: HSBC, Bangalore. Project: Data Engineering and Visualization. Conducted data curation for the Ontology project, facilitating automatic SQL Query Generation, and implemented machine learning models for data analysis. Automated Unit Testing Functionality using Python and led User Acceptance Testing (UAT) for various projects.

Project: Risk Analytics. Designed and implemented a scalable Python application for automating Data Driven Testing controls, resulting in a 99% efficiency improvement. Developed LDA-based Topic model to extract abstract topics from testers' reasons for testing delays. Created standard Python scripts for data cleansing and pre-processing using NLTK and Spacy. Conducted QA activities for Risk Analytics reports using SAS EG and Python.

Project: AML (Anti-Money Laundering: FATCA/CRS). Created machine learning models to generate reports for Fraudulent Transactions. Transferred and transformed data to SQL server from Legacy system/Database (DB2) for tax compliance reports. Developed and maintained Tableau Dashboards for tax compliance reports.

Client: AETNA (US based Healthcare & Insurance Company). Project: Automatic Claims Adjudication System. Developed machine learning models for claims reports, enhancing accuracy and reducing claims processing time. Prepared ad-hoc reports using the DB2 database and implemented machine learning techniques for data analysis.