Works / Archive
An archive of systems, studies, and interdisciplinary experiments.
Each project is framed as a larger scene rather than a small equal-weight card, so the archive feels curated, directional, and editorial.
Machine Learning Research
Predicting Fraudulent Transactions: A Comparative Study
This project compared several machine learning approaches for fraudulent transaction prediction on a dataset with more than 6.3 million rows. The work included preprocessing, feature selection, and evaluation across logistic regression, random forest, XGBoost, stacking, and CNN models.
Compared logistic regression, decision tree, random forest, XGBoost, stacking, and CNN approaches on the same fraud-detection task.
Built a preprocessing workflow with duplicate removal, one-hot encoding, class-ratio adjustment, and recursive feature elimination.
Exhibit 01
Model Atlas
2025
Project Signal
A fraud-detection study comparing classical ML models, ensemble methods, and a CNN on large-scale transaction data.
Stack
Python
pandas
scikit-learn
01
Assistive Technology
Braille Calculator Initiative
Working with a program supported by the Chinese Academy of Sciences, I helped design and refine a Braille-based calculator for students at the Beijing School for the Blind. The work combined interface simplification, software transmission improvements, testing with real users, and a broader lesson about how educational technology should support actual learning rather than only technical convenience.
Designed a calculator workflow to simplify two-digit multiplication for visually impaired students.
Improved software-side data transmission and iterated through user testing in real classroom settings.
Exhibit 02
Access Field
2026
Project Signal
An accessibility-focused calculator project designed to help visually impaired students perform two-digit multiplication more efficiently.
Stack
Accessibility Design
Prototyping
Software Testing
02
Machine Learning Research
Credit Risk Modeling Research
Through the Algorithm for Big Data program, I studied topics such as data transmission, reconstruction, logistic regression, CNNs, and transformers. I then applied those methods to credit risk prediction, comparing model behavior and performance. The project strengthened both my technical interest in machine learning and my habit of evaluating models through practical outcomes rather than abstraction alone.
Studied machine learning concepts including logistic regression, CNNs, and transformers.
Applied those models to credit risk prediction and compared performance across approaches.
Exhibit 03
Risk Signals
2025
Project Signal
A research project on machine learning models for credit risk prediction, developed through advanced study in algorithms and data.
Stack
Python
Machine Learning
Data Analysis
03
Community Initiative
Science, Arts, and Philosophy Club
I founded this club to create space for conversations that connected computer science with philosophy, design, and social responsibility. We held seminars for audiences of more than 100 people and discussed topics such as AI ethics, inequality, and how technological progress affects ordinary communities. It reflects the way I like to approach technical work: not only by building systems, but by questioning who they serve.
Founded an interdisciplinary club linking technology with aesthetics, philosophy, and ethics.
Organized seminars for audiences of more than 100 participants.
Exhibit 04
Public Forum
2025
Project Signal
A student-led club exploring technology, social computing, aesthetics, and ethics through interdisciplinary discussion.
Stack
Leadership
Public Speaking
AI Ethics
04
Education & Outreach
Chemistry Thinks Big
While teaching in Xichuan, I adapted chemistry lessons to work with limited equipment by treating everyday environments as laboratories. Students explored pH testing, filtration, catalysts, and material behavior using household and local materials. We documented the work in a project book called 'Chemistry Thinks Big,' which captured the broader lesson that creativity and resilience can expand what education looks like.
Designed chemistry activities using household and local materials when formal lab resources were limited.
Introduced students to pH testing, filtration, catalysts, and material behavior through hands-on teaching.
Exhibit 05
Field Lab
2024
Project Signal
A hands-on chemistry teaching initiative developed during volunteer instruction in Xichuan.
Stack
Teaching
Curriculum Design
Volunteer Work
05
Next
If one of these threads connects to your work, continue the conversation.
Contact
Open the contact page for recruiting, collaboration, or project discussion.