Skip to content
View lavine888's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report lavine888

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
lavine888/README.md

Lavine Xie — AI Products and Quantitative Systems

Portfolio Email Location Profile Views

English · 简体中文

♓ About Me

I have a background in Mathematics and Applied Mathematics and am currently pursuing an MSc in the Department of Computer Science at City University of Hong Kong. My work focuses on two connected tracks: AI products and quantitative systems.

I enjoy turning ambitious ideas into working systems—from zero-to-demo AI products to Python-based factor research. My approach connects technical judgment with product context, rapid experimentation, growth thinking, and clear stakeholder communication.

AI Products Quantitative Systems
Human-centered AI applications, agents, and rapid product prototypes. Python-based factor research, signal evaluation, and reproducible analysis workflows.

Across both tracks, I prefer evidence over storytelling alone: define the real problem, build the smallest credible system, test it with real users or measurable signals, and improve it through iteration.

🌳 Featured Projects

2nd Place in Track · Hong Kong Physical AI Hackathon · Team Project

A relationship-centered AI product for preserving authentic life records and entrusting them to loved ones with consent and restraint—not digital resurrection.

First Prize · Agent Builder Hackathon, Shenzhen · Hosted by StepFun

An AI coding collaboration product that brings agent execution, shared project context, and team review into one live workflow.

PandaAI Quant Factor Competition

National Runner-up · Top 1%

A Python factor-research workflow for data cleaning, IC / IR signal evaluation, and competition return validation.

30-hour Hackathon Prototype

An AI networking product that structures professional identity and helps users discover higher-value connections.

AI-assisted Finance Learning Prototype

A game-based product that turns candlesticks, market sentiment, and trading strategies into an explorable learning experience.

🛠️ Tech Radar

Skills


Claude OpenAI API
Layer What I Work With
Programming Python, JavaScript, HTML, CSS, MATLAB, R
AI Products LLM Applications, Agents, NLP, Rapid Prototyping, Demo Design
Quantitative Systems Factor Research, Statistical Modeling, Time Series, IC / IR, Return Validation
Workflow Git, GitHub, Codex, Claude

🎓 Education

⚡ Current Direction

  • Shipping AI products with clearer user problems, stronger demos, and real feedback.
  • Building cleaner quantitative research loops from data preparation to signal evaluation.

📫 Contact

Open to AI product, quantitative research, and early-stage collaboration.

Portfolio · lavinexie@foxmail.com

Pinned Loading

  1. bull-bear-exchange-island bull-bear-exchange-island Public

    A game-based finance learning prototype that turns candlesticks, market sentiment, and trading strategies into an explorable 3D world.

  2. loop loop Public

    Forked from wujiajunhahah/loop

    Wozai: a relationship-centered AI product for preserving and entrusting authentic life records. 2nd place in the Hong Kong Physical AI Hackathon track.

    TypeScript

  3. skill-buffett-moat-screener skill-buffett-moat-screener Public

    Point-in-time, fail-closed Buffett moat hard screener for Shanghai and Shenzhen A-shares using PandaData.

    Python

  4. skill-shortterm-mean-reversal skill-shortterm-mean-reversal Public

    Auditable Q58 five-session A-share short-term reversal factor research with PandaData, point-in-time controls, cost-aware backtesting, and reproducible validation.

    Python