Ethics of AI development. This project explores a multitude of ethical dimensions to artificial intelligence and is split into three key components: an exploration of the ethics of AI development, a section dedicated entirely to learning about bias in programming and AI, and a critical examination of key social and legal questions.

Meteorology Prediction Using Weather Data. The spatial data includes features like ocean temperature, precipitation rate, lake inflow, etc. Meteorology experts have developed great models for predicting a lake’s inflow using dynamic regression and WRF-chem model, but the field of predicting precipitation rate and many other features are still under exploration. Using the satellite data from NOAA, we combine machine learning techniques and domain knowledge in spatial data to explore the discipline further.

China Data Institute We work together with China Data Institute to gather, describe, and analyze country-level data in order to gain insights on the economic, political and social development of a country.

Predicting the Popularity of Apps in the App Store. Our objective is to build up models to help advertisers find the potential popular apps in App Store. We scraped data from app store through the iTunes API, and applied feature engineering to it via text analytics. We defined apps with top 10% performance as the advertisers’ goal. But in the real world, users can customize the quantile-based on their own needs. Then we performed linear and logistic regression, neural network, KNN, decision tree and random forest.