Ren Zuo

1. Visualizing, mapping, and supporting understanding of a standard table from the D&B Worldbase. 2. Leveraging both desktop visualization tool (PowerBI) and web-based visualization package (D3) to support business intelligence analysis. 3. Designing an interactive visual analytics system which supports the sales team to get quick insights about a company's structure and compare entities inside the company.

1. Developed latest algorithms to realize automatic Entity Matching between blacklists and a 5MM+ entity database and improved performance through multiprocessing; the solution increased recall by ~90% and is applied in PwC risk management projects. 2. Cleaned 73MM+ patient records through customized data manipulation process; conducted statistical inference to enhance data integrity, imputed missing value using k-NN and Soft-Impute, and performed feature engineering on over 2000 features.

Publication: HistoQC: A quality control pipeline for digital pathology slides, Second Author; 1. Designed a data exploratory workflow and implemented a visual interface [Web] to support High-Dimensional Data Analysis and digital pathology slides quality control; the solution won the 2018 ESDIP Digital Diagnostics Award. 2. Established a public data sharing platform [Flask & MySQL] for pathologists to share and retrieve digital pathology slides.

1. Led a team to build an interactive dashboard for a Fortune 100 company, which supported business intelligence and presented insights to the global management team. 2. Created an automatic pipeline to conduct NLP for a national research center, performed Semantic Analysis to identify factors of interest; increased reports processing speed by 10+ times. 3. Redesigned the data operation procedure and developed a management information system for the China Office of a leading university.

1. Designed a hybrid recommender system and led the technical team in implementation; the module was highly recognized and is globally used by the client. 2. Streamlined ETL process to merge marketing data from different sources and increase database maintenance efficiency. 3. Optimized process control by developing an activity tracking toolkit, which was selected as the only practical tool into the final deliverable.

Thesis: Flow Visualization on the Smart Card Record of Subway Transportation; 1. Performed Spatiotemporal Analysis based on a self-developed geographical visualization system [D3.js]; extracted urban population flow patterns and developed city management insights from 90GB+ subway card records. 2. Developed SVM-based visualization system, conducted anomaly detection, and automated data cleaning process on ~2TB taxi GPS dataset; implemented clustering models to support visual analytics

1. Created VBA scripts to parse, match, and to segment marketing data and generated standard visual reports to support marketing analysis; the tool was embedded into the department's standard data manipulation process. 2. Proposed sales recommendations for a major product based on policy investigation, industrial data visualization, and compliance analysis; informed decision-making for the senior management team.

GPA: 4.11/4.33 Specialization: Business Intelligence and Data Analytics

GPA: 3.37/4.00 Specialization: Intelligence Science and Technology