Wendy Han

Background

About Wendy Han

Over 7 years of cross-industry experience in Data Science, Machine Learning, Data Engineering, and Analytics, with a proven track record of delivering business impact in healthcare, retail, supply chain, and digital marketing sectors.• Skilled in Python programming with strong knowledge of object-oriented programming, concurrency/multithreading, regular expressions, scripting, and API development. Proficient in data processing and pipeline development using Pandas, NumPy, and regex, with experience building scalable ETL workflows.• Advanced SQL expertise, including writing optimized queries, complex joins, CTEs, window functions, stored procedures, and performance tuning for analytical workloads. Hands-on experience with Snowflake, Google BigQuery, Amazon Redshift, and PostgreSQL/MySQL, as well as dbt for transformation and modeling.• Hands-on experience in applying advanced machine learning and AI/LLM methods, including Gradient Boosting (85% churn prediction accuracy), CNNs (95.7% cancer diagnostics accuracy), and Retrieval-Augmented Generation (RAG) pipelines for intelligent chatbots that reduced product returns and customer service costs by up to 30%.• Designed and deployed data pipelines and machine learning models on Google Cloud (BigQuery, Vertex AI, Cloud Functions) and AWS (S3, Lambda, Redshift), with additional exposure to Azure Machine Learning and Azure Storage.• Built automation workflows using Bash scripting and Airflow, enabling efficient data ingestion, transformation, and monitoring across structured and unstructured datasets.• Strong experience with big data technologies, including Hadoop, Apache Spark, and Kafka, for parallelized data processing and real-time streaming analytics.• Proficient in data visualization and BI platforms including Tableau, Power BI, and Looker Studio, developing interactive dashboards and reports for executive-level decision-making.• Experienced in working with diverse data formats such as CSV, JSON, XML, Parquet, and integrating them into cloud-based data warehouses and analytics pipelines.• Developed interactive applications and front-end solutions using React, Streamlit, and R Shiny, bridging machine learning outputs with user-facing interfaces.• Skilled in software engineering practices such as Git-based version control, GitHub Actions CI/CD, code reviews, and agile workflows.• Applied data mining and statistical modeling techniques such as clustering, regression, classification, and survival analysis to both numerical and textual datasets.