Hetvi Shah

Built ETL pipelines using Python/SQL to automate data extraction and transformation, improving workflow efficiency by 25%. Analyzed complex data sets from various sources to identify trends, patterns, and insights that informed business decisions. Managed and optimized databases including MySQL and Microsoft SQL Server, with expertise in data warehousing and data pipelining development. Designed Tableau and Power BI dashboards that enhance data-driven decision making by 30% for cross-departmental teams. Implemented data quality control measures and KPIs to ensure accuracy and reliability of data, utilizing Git for version control, while monitoring data security. Collaborated with cross-functional teams to understand business requirements and translate them into data-driven solutions, leveraging Agile/Scrum methodologies.

Developed predictive models using time series analysis and regression techniques, boosting customer satisfaction by 25%. Assisted in developing classification models using Scikit-learn and XGBoost for customer segmentation, achieving high accuracy. Implemented and maintained recommendation models using Python and TorchServe, contributing to a 15% increase in user engagement. Conducted A/B testing to measure the impact of new ML models, resulting in increased conversion rates and improved customer engagement. Built ETL pipelines using Apache Spark and Airflow to process structured and unstructured data. Managed the analytics cycle with advanced data analysis, statistical modeling, and prediction algorithms. Collaborated with senior engineers to migrate ML pipelines to AWS SageMaker, reducing training time by 35%. Projects included AG News Category Prediction Microservice and Text Classification API, deployed on Google Cloud Run.