Projects
Projects range from self-written coursework to AI-assisted tools and current competition research. Each page explains the problem, the choices I made, and what I learned from the result.
Neural Debris Removal Competition
An active Kaggle computer-vision project studying how to reduce a poisoned RetinaNet detector's unwanted behavior while preserving useful detections.
CSI 300 Portfolio Modeling Challenge
An active competition project for ranking CSI 300 candidates and assigning a five-stock portfolio with point-in-time features and walk-forward validation.
Local DeepSeek Coding Agent
A Python MVP for learning how coding agents work, with a CLI, tool-calling loop, workspace file tools, shell/test execution, git diff output, and safety checks.
Tencent AI-HR Growth Demo
An AI-assisted Tencent AI-HR demo that turns newcomer profiles into 30-60-90 day growth paths, mentor feedback, HR views, and a review-friendly walkthrough.
F1 Pit Stop Prediction
A Kaggle tabular-ML project that predicts whether a driver will pit on the next lap, with race-aware validation and repeatable experiments.
Airbnb Listing Price Modeling
A notebook-based tabular modeling project for predicting New York City Airbnb listing prices.
NLP Text Analysis and Topic Modeling
A coursework-style NLP notebook project combining embeddings, similarity analysis, preprocessing, and LDA topic modeling.
A-Share Data Analysis Tools
Three AI-assisted Python tools for exploring A-share market data: an intraday dashboard, a broader research dashboard, and an AKShare API checker.
Local Qwen Chinese Fiction Pipeline
A local Qwen writing workflow controlled by Python, built to simulate agent-like planning, memory, and continuation for fiction generation.
ZiyangZhou.me Portfolio Website
A bilingual portfolio that organizes projects, GitHub links, short write-ups, resume access, and personal background.
ChatGPT API Browser Bridge
A local API/browser bridge experiment for connecting local scripts with ChatGPT web workflows and reducing repeated context entry.
Recipe Text Clustering
An unsupervised text clustering project comparing bag-of-words and sentence embeddings for recipe-name clustering.
Adult Census Preprocessing Pipeline
A supervised learning pipeline project focused on preprocessing, leakage prevention, and baseline comparison.
CPSC 221 Hash Tables Lab
A C++ lab implementing separate chaining and linear probing hash tables with text-analysis exercises.
CPSC 221 AVL Trees Lab
A C++ lab implementing a self-balancing binary search tree with rotations, insertion, removal, and tests.
CPSC 221 Heaps Lab
A C++ lab practicing array-backed heap operations, priority-queue behavior, and index arithmetic.
CPSC 221 Graphs and Union-Find Lab
A C++ lab covering graph representation, graph tools, weighted edges, and disjoint-set structures.
Sleep Tracking App
A Java application for recording sleep, setting goals, and reviewing habits over time.
China Glass Futures Quantitative Strategy
A trading-strategy research project focused on strategy logic, backtest review, drawdown, market regimes, and parameter stability.
Logistic Regression Text Classification
A tweet classification project moving from a dummy baseline to bag-of-words logistic regression.
Spotify Decision Tree Modeling
A compact decision-tree classification exercise using Spotify-style track attributes.
Handwritten Character Recognition App
A student computer-vision app that trains a compact PyTorch CNN on EMNIST and predicts characters drawn in a Pygame window.