Anna L. Email & Phone Number

Menlo Park, Ca, Us

Building Trust (Privacy and Integrity) in various spaces (Business, Metaverse/VR, Ads)

Seattle, Washington, Us

• Developed a source-to-target mapping recommendation engine using various machine learning models and frameworks (scikit-learn, Tensorflow, Keras) in Python to smooth ETL mapping process• Developed a full stack data profiling web application in Python, Vanilla JS and AWS (S3, Lambda, Step Functions, Glue, Athena, etc) to assess source data quality• Launched a centralized data analytics platform (JupyterHub) on AWS EC2 to support internal analysts to run and share SQL queries and analyses.• Proof of Concept: applied anomaly detection machine learning techniques to detect outliers in mapped data for quality check.

Seattle, Washington, Us

Automated file conversion/cleansing/uploading/classification process to smooth ETL process• Uploader: Built a desktop application using Python to upload standardized source files to SQL Server and generate customized supporting tables by users' selection• File Classifier: Implemented a backend algorithm in Python to auto-classify source files based on file format

Chicago, Illinois, Us

• Development of web-based interactive BI dashboards in Python (Bokeh)• Development of data pipelines/tools in Python to pull data from various sources for dashboards• Front-end development of a project tracker in AngularJS for senior management

Greensboro, Nc, Us

• Analyzed key features of underwriting decision models• Built classification models to predict underwriting decisions using R and R packages• Mined rules from data to discover relations between variables (Association rule learning)• Extracted data from XML

Greensboro, Nc, Us

Worked within a BI group, a team that is responsible for Corporate Reporting and Analytics. The BI teams maintain Data Warehouse, the BI Portal, and central operational reporting portals. BI reports serve a wide range of departments within the company and are also shared with customers such as banks and credit unions.Projects: • Built statistical models to predict the daily application volumes; •• Researched about Automated Underwriting Process: automating the process of reviewing applications and underwriting to increase the working efficiency of underwriters by applying machine learning algorithms• Presented results and findings to directors and C-level

Berkeley, Ca, Us

Contributed to the R package EML, an R package for reading, writing, integrating and publishing data using the Ecological Metadata Language (EML) format.

Berkeley, Ca, Us

•• Assisted students understand and finish lab, homework assignments, and projects in CS 61A

Bachelor’S Degree, Applied Mathematics And Statistics

Master Of Science - Ms, Computer Science