Causal Discovery and Deep learning: Ensemble Deep Learning for Stock Return Prediction in Volatile Markets

Financial market volatility, driven by economic conditions, corporate shocks, and investor behavior, makes stock return forecasting highly challenging.

Traditional methods, such as macroeconomic analysis and sentiment analysis, have limitations in capturing the complex relationships between stock returns and external factors.

Our goal is to develop an advanced stock return prediction framework that leverages causal discovery algorithms to enhance interpretability and accuracy.

link to github

link to report

link to poster

Storytelling Visualization: Campaigning on Twitter

Explore the “word war” of the 2016 election through this storytelling project! Using NLP, sentiment analysis, and interactive visualizations, we uncovered how candidates turned Twitter into a campaign battlefield, shaping the outcome one tweet at a time.

A Demo

Predictive task: Advancing Multimodal Sentiment Analysis through Enhanced Sarcasm Detection

Sarcasm Hard to Catch? Not Anymore! This project combines text and audio to detect sarcasm, making sentiment analysis easier. We thoughtfully designed every step, from data collection and feature engineering to model building. With our sarcasm detection model, we’ve cracked the code of complex emotions. Because sometimes, tone says it all!

Casual Discovery: Algorithm Comparison on Simulated Mental Health and Remote Work data

Dive into this project to discover how well different causal algorithms uncover relationships between variables! Explore how a person’s work enviroment, daily habits and mental health connect in our simulated dataset.

Data Minning: Used Car Price Prediction

Ever wondered what drives the price of a second-hand car? We built an XGB Regressor that beat baseline models by over 50% in RMSE. From mileage to color quirks, we unraveled the secrets behind used car pricing with data minning! 🚗✨

Storytelling Visualization: Pattern of US City Names

Discover how US cities got their names from around the world! Explore migration and immigration patterns through the checkboxes, hover to the points for details, and read the story to see how history shaped these connections.