Xiao (Rachel) Bai

M.S. in Applied Data Science @ USC | B.S. in Statistics & Economics @ UofT | Data scientist | Actively Seeking Full-time 2026

United States

About

USC graduate in Applied Data Science, building expertise in machine learning, large-scale data pipelines, and analytical dashboards. Recently evaluated the suicide screening program as a data scientist intern at PCCI by processing EHR records and engineering clinically grounded features, and delivering models and visualizations that informed clinical and policy decisions. Previously developed an interactive crime dashboard for USC Annenberg Media and held analytics internships at GoodIdea, Wilo, and Meituan, where I used SQL, Python, Excel, and Tableau to drive digital marketing, sales, and HR insights. Passionate about turning messy real-world data into reliable, production-ready tools that support smarter decisions. If you happen to be curious about how using data can connect cultures and drive impact — let's chat!

Experience

  • Data Scientist at PCCI
    May 2025 - Aug 2025 · 4 mos

    Evaluated suicide screening program by building ML pipelines. Processed EHR records to engineer clinically grounded features and standardized training/evaluation across cohorts. Partnered with clinicians and leadership, delivering visualizations and presentations that informed policy decisions.

  • Web Developer at USC Annenberg Media
    Jan 2025 - Apr 2025 · 4 mos

    Developed an interactive crime dashboard by transforming raw DPS incident reports into clean, structured data and published on Annenberg Media’s website, enabling students and staff to explore campus safety patterns in real time. Performed data cleaning and imputation, persisted processed records in MongoDB for efficient querying, and automated ingestion of university-provided PDFs into a database exposed via a public API. Implemented a JavaScript-based heatmap interface using Node.js and Cloudflare to deliver a performant and accessible front-end experience.

  • Data Scientist at GoodIdea Media
    Oct 2023 - Dec 2023 · 3 mos

    Performed headroom analysis targeting on digital marketing optimization; Utilized Python & SQL to initiate interface interaction optimization strategies through analyzing million-level clickstream; Developed an automated ETL pipeline for performance monitoring; automated the updating of summary tables on the cloud platform

  • Data Analyst at Wilo Group
    May 2022 - Aug 2022 · 4 mos

    I worked on applying sales performance analysis across different stages, visualized sales performance metrics patterns interactive Tableau dashboard, as well as completed data cleaning and processing via Excel functions to analyze the inventory data from Wilo’s regional distribution center.

  • Human Resources Analyst at Meituan
    Sep 2021 - Dec 2021 · 4 mos

    Mainly responsible for analyzing weekly enterprise recruitment status report, summarizing enterprise-wide HR metrics, e.g., interview-to-offer rate, turnover rate, and output per person/group, etc., and presented the report to HR group lead