Full Page Image

I'm Yishan Cai

 








About


Hi there, I am Yishan Cai(蔡依珊). I am currently pursuing a double major in Data Science and Math - Probability & Statistics at UC San Diego, set to graduate in June 2025. My academic journey has been shaped by a profound passion for understanding patterns, extracting insights, and deriving meaning from data. I am actively seeking roles in data analysis and machine learning that align with my skills and aspirations.

I am always eager to embrace new challenges and connect with diverse perspectives. If you're interested in collaborating or simply want to discuss data science, art, or adventures, feel free to contact me at yic075@ucsd.edu. Let's create something amazing together!

I enjoy painting and playing the pipa, and I'm a fan of travel and photography.

View my résumé (updated in Feb. 2025)



Education

University of California, San Diego

September 2021 - Expected June 2025

Data Science
Bachelor of Science, Halıcıoğlu Data Science Institute (HDSI)

Probability & Statistics
Bachelor of Science, Math department



Experience

Business Analyst Intern

Tencent Technology (Beijing) Co., Ltd, Qidian Product Department
June 2024 - September 2024

  • Participated in the optimization of the Customer Data Platform (CDP) and Marketing Automation Platform (MA) for Qidian Marketing Cloud, a B2B SaaS Intelligent Marketing Platform
  • Crafted interview outlines, performed needs analysis, and synthesized findings into requirement documentation
  • Developed and maintained insight dashboards with SQL & Tableau to monitor user behavior metrics and performance trends
  • Led User Acceptance Testing (UAT) with R&D team, documented technical requirements, and updated product documentation



    • Large Language Model Data Intern

    Fourth Paradigm Technology Co., Ltd.
    June 2023 - September 2023

  • Compiled and summarized text data characteristics from social media platforms such as Xiaohongshu, Zhihu, and Toutiao, and performed large-scale unstructured data cleaning of 923 GB using Python
  • Conducted sampling evaluations on the cleaned corpus, producing 45+ reports, improving accuracy by ~22% through optimization
  • Constructed JSON templates for Q&A tasks including text summarization, sentiment analysis, information extraction, and created 2,000+ manually crafted prompts and answers for supervised fine-tuning



    • Research Assistant

    Chinese Academy of Agricultural Sciences, Institute of Vegetables and Flowers
    August 2023 - September 2023

  • Implemented Principal Component Analysis (PCA), and developed Score Plot and Loading Plot to analyze the contribution value of different indicators of Feng-Hua Rose
  • Derived correlation heatmaps using R to visualize the effects of three different arbuscular mycorrhiza fungi (AMF) on the morphology and physiology of rose



    • Research Assistant

    Beijing Forestry University, School of Landscape Architecture
    Advisor: Prof. Wei
    July 2020 - August 2020

  • Digitally captured records for six historical sites and designed satisfactory scales based on the Oliver Tourist Satisfaction Model to gather 250+ survey data via questionnaire
  • Performed data cleaning and sorting, descriptive analysis, and linear regression



    • Website Builder

    China House
    Advisor: Dr. Zhu, Stony Brook University
    March 2020 - June 2020

  • Established an official chinese website to show the current situation of Borneo rainforest and orangutan
  • Developed structure and style of the website via HTML, JavaScript, and CSS

    • Copyright Yishan Cai © 2024