Sr. Data Scientist
▪ Transitioned all ETL processes from Matillion to a custom-developed Python tool, incorporating advanced error logging and time tracking features to enhance the maintenance of the production database.▪ Successfully created ETL pipelines to make sure data is up to date to production databases.▪ Fabricated a classification model using XGboost classifier and automated machine learning ops to make sure model stays above the threshold model metrics using CI/CD methodologies.▪ Successfully implemented NLP methods to use bag of words, lemmatization and VADER libraries to get sentiment analysis, word cloud and automated topic detection.▪ Refactored legacy sql scripts to make them more efficient and reduce redundancies.▪ Successfully configured dev ops for data team using github to have version control, QA stage and push to production from Github to snowflake as soon as sql script is changed.▪ Generated synthetic data using deep learning methods to successfully anonymize data for product demos.▪ Successfully automated public API to incorporate external data into dbms tools to have extra data fields for machine learning models.