Coco (Xiaoyu) Huang

Realized Volatility Prediction and Graph Data Mining

Graph Neural Networks(GNNs) are very powerful, but what if the graph is nonobservable?
We proposed a new model integrating graph discovery data mining techniques and GNNs to overcome limitations in graph structures for machine learning modeling tasks, and applied it to realized Volatility Prediction.

• Learn more

Recommender System for Advertising

If a supplement brand and gym wear brand hired the same influencer, does it help if they hire another together?
We developed a Graph Neural Networks (GNNs) based recommender system connecting businesses with social media influencers by learning various aspects of their social media behaviors such as text caption, image, and the social relationship among influencers and brands.

• Learn more

Dashboard to Discover Dynamic Network of Stocks

Can we discover how the relationship among stocks changed over the past decades using only data?

We produced the stock network discovery app that allows you to discover the latent network within any selection of stocks during any period of time.

• Dashboard

Smooth Laplacian Python Package

We created a Python package that implements the graph learning algorithm in Learning Laplacian Matrix in Smooth Graph Signal Representations.

• Code

A scraper

We created a scraper to politely collect public Instagram users' info, posts, and pictures without invasion of privacy.

• Code