Hello, I'm
Katherine CAO (Yimeng)

✨

Bridging Data, Finance, and AI. Turning complex data pipelines and LLM systems into strategic, decision-making value.

Contact Me LinkedIn GitHub
Katherine Cao Yimeng Avatar
[ ABOUT ME ]

Bridging Data, Finance, and AI

Hi, I'm Yimeng "Katherine" Cao (曹译萌) — a curious, fast, and lifelong learner passionate about bridging Data, Finance, and AI. Having graduated from Shanghai University of Finance and Economics (SUFE) and completed my Master's degree at Nanyang Technological University (NTU, Singapore) in Jan 2026, I turn complex data into actionable insights for forward-thinking organizations.

[ ACADEMIC BACKGROUND ]

Academic Background

NTU Logo
MASTER OF SCIENCE (MSc)

Nanyang Technological University

MSc in Business Analytics

Jul 2024 – Jan 2026 • Graduated (Jan 2026) • Singapore

SUFE Logo
BACHELOR OF BUSINESS (B.B.A.)

Shanghai University of Finance & Economics

Bachelor in Business Analytics

Sep 2020 – Jun 2024 • Graduated • Shanghai, China

[ CAREER ROADMAP & INTERNSHIPS ]

Internship Journey Roadmap

Canalys Logo
JAN 2023 – APR 2023

Market Analyst Intern @ Canalys, Shanghai

Excel & SQL Web Scraping Market Research Collaboration
  • Collected and consolidated multi-vendor market data to support quantitative industry analyses.
  • Leveraged web scraping techniques to gather global smartphone and IoT hardware intelligence.
  • Collaborated across international teams to deliver actionable, data-driven executive presentations.
eBay Logo
MAY 2023 – NOV 2023

Business Analyst Intern @ eBay, Shanghai

SQL & Databases Tableau A/B Testing Causal Inference GMV Growth
  • Optimized analytics queries and seller performance pipelines to drive operational decisions.
  • Engineered interactive Tableau dashboards empowering 6,000+ cross-border sellers with actionable growth metrics.
  • Managed seller engagement growth initiatives, generating measurable improvements in overall GMV.
BigOne Lab Logo
APR 2024 – JUL 2024

Data Product Intern @ BigOne Lab, Shanghai

Tableau BI Python NLP Sentiment Analytics E-Commerce Insights
  • Built automated BI dashboards to track brand health and consumer performance metrics across platforms.
  • Performed Python-based NLP sentiment evaluation to inform client product and investment strategies.
Temasek Logo
MAR 2025 – DEC 2025

Data Analyst Intern @ Temasek, Singapore

AI RAG LLMs Copilot Studio Power BI Python RPA Snowflake
  • Architected an enterprise-grade AI Chatbot and a RAG+LLM extraction workflow for financial document processing.
  • Conducted process analytics and implemented machine learning models to detect bottlenecks and optimize workflows.
  • Developed interactive Power BI dashboards to track key performance and financial evaluation metrics.
  • Implemented RPA automation workflows to streamline document handling and regulatory compliance.
[ TECHNICAL SKILLS MATRIX ]

Core Toolkit & Stack

Generative AI & LLM Systems

RAG (Retrieval-Augmented Gen) Prompt Engineering Fine-Tuning (PEFT, LoRA) LangChain Hugging Face Transformers Llama 3 / Claude / OpenAI API Vector DBs (Chroma DB, Milvus) Microsoft Copilot Studio

Machine Learning & Modeling

Scikit-learn (Random Forest, XGBoost, LightGBM) Causal Inference A/B Testing & Hypothesis Testing Predictive Modeling & Anomaly Detection Markov Chain Analytics

NLP & Computer Vision

spaCy NLTK Vision-Language Models (Fashion-CLIP) Text Mining & Sentiment Evaluation

Programming & Frameworks

Python R SQL (Snowflake, MySQL, Oracle) Git / GitHub PyTorch TensorFlow

Data Visualization & BI

Power BI (DAX) Tableau Excel (Advanced Data Modeling) R Shiny Dashboards

RPA & Cloud Platforms

UiPath RPA Power Automate AWS (S3, EC2, SageMaker) Oracle Cloud Infrastructure Snowflake Data Warehouse
[ CERTIFICATES & OFFICIAL BADGES ]

Professional Certifications

AI & MACHINE LEARNING

AI & Data Science Credentials

FINANCE & RISK

Financial Risk Manager (FRM)

RPA & AUTOMATION

Automation Diplomas

COMPETITIONS & VOLUNTEER

Others & Leadership

[ FEATURED PORTFOLIO PROJECTS ]

AI Systems, Web Apps & Repositories

AI Playbook • Fullstack Architecture
409 Tech Terms ➔ AI Agents ➔ Obsidian Vault
GITHUB REPOSITORY • AI KNOWLEDGE BASE

Vibe Coding Playbook

Comprehensive AI & Fullstack engineering playbook featuring 409+ tech terms, AI Agent Frameworks, System Prompt Engineering, and Obsidian Vault integration.

View Architecture & Details ➔
Markdown • LaTeX • Vercel App
Markdown Outline ➔ KaTeX Engine ➔ Mind Map Sync
VERCEL LIVE APP • AI MIND MAPPING

Outlinia: AI Mind Mapping Web App

Dynamic Markdown & LaTeX formula mind mapping web app featuring bidirectional outline syncing, KaTeX math equations, table rendering, and multi-format exports.

View Architecture & Details ➔
Python • ML • Snowflake
Workflow Data ➔ ML Analytics ➔ Power BI
GITHUB REPOSITORY • PROCESS ANALYTICS

End-to-End Process Analytics

Analyzed and optimized complex business processes across multiple databases to identify bottlenecks, improve efficiency, and support strategic decision-making.

View Architecture & Details ➔
SwiftUI • HealthKit • Live Activity
Sleep Schedule ➔ Curtain Prep ➔ HealthKit Sync
NATIVE IOS APP • LOCAL PROJECT

Healio: Sleep Transition Companion

Native iOS app built with SwiftUI, HealthKit, and DeviceActivity. Features pre-bedtime Curtain rituals, Gentle/Strict app shielding, and Live Activity Dynamic Island countdowns.

View Architecture & Details ➔
RAG • Chroma Vector DB • Python
Legal PDF ➔ Chroma Vector DB ➔ LLM Compliance
LLM COMPLIANCE • LOCAL PROJECT

AI Legal Document Extractor

RAG-powered intelligent legal document extraction and compliance analysis system parsing complex agreements using Chroma DB and Hugging Face / OpenAI models.

View Architecture & Details ➔
UiPath • SharePoint
Requests ➔ Classifier ➔ Auto Submission
GITHUB REPOSITORY • RPA AUTOMATION

Automated File Submission

Workflow automating the process of retrieving incoming requests, downloading files, classifying them, and submitting them to appropriate platforms.

View Architecture & Details ➔
UiPath • Web Scraping
Shopee & Lazada ➔ Scraper ➔ Email Intelligence
GITHUB REPOSITORY • PRICE INTELLIGENCE

Automated Competitor Price Tracking

Extracts product prices from Shopee and Lazada and delivers timely, accurate, and consistent pricing data to stakeholders through automated emails.

View Architecture & Details ➔
Python • R Shiny Dashboard
Smart Meter ➔ API ➔ Shiny Visualization
GITHUB REPOSITORY • DATA VISUALIZATION

Electricity Consumption System Demo

Demo MVP simulating smart meter readings and visualizing household electricity usage through an interactive Shiny dashboard with API management.

View Architecture & Details ➔

Contact Me

Feel free to reach out via email or LinkedIn.

Email: yimeng_cao@outlook.com

LinkedIn GitHub