Info 251

Applied Machine Learning

(Fall 2017)

Project Gallery

Forecasted Air Pollution using LSTM Sequence to Sequence
Deep Air
Forecasting air pollution in Beijing, China, using deep neural networks consisting of LSTM layers.
aspiringteaser.png
Helping University Career Services Target the Right Mix of Companies
Based on analysis of AMCAT Scores of millions of engineering students in India and their academic scores, we built a machine learning model that can be used by...
beijing-smog.jpg
Identifying Air Pollution Data Manipulation in China
Can machine learning techniques be used to help identify historic manipulation of air pollution data by officials in China?
™ Wikimedia Foundation, Inc.
Looking for a Needle in a Haystack: Predicting Wikipedia Edits
Every day, fewer than one in 1,000 Wikipedia articles gets an edit. Predicting which one will be edited today is an exciting and hard task.
cycle_2.jpg
MoBike
Predict lifetime of shared bicycles based on historical trips, weather, and crime data to help bike sharing companies maintain a healthier sharing system.
Opportunities for Arbitrage in the Beijing Housing Market
We build a novel real estate price dataset that contains a large sample (over 60,000 data points) of data from two major cities in China, Beijing and Shanghai...
Most Important Features Associated with User Dropout
Predicting User Dropout in Digital Health
Use machine learning to predict user dropout in digital health. 
Show Me What You Got: Predicting Music Popularity
screen_shot_2017-12-11_at_8.05.38_pm.png
The Eyes Have It (or do they?)
Eye tracking technology has the potential to offer more seamless interactions as input for a variety of software applications, but is there a cost to user...
screen_shot_2017-12-11_at_18.26.05.png
Understanding the factors that influence L1 work visa for US
We take a deep dive into understanding the factors that impact the acceptance of a USA L1 work authorization visa
What are Predictors of Medication Change and Hospital Readmission in Diabetic Patients?
Can machine learning find factors related to medication change and hospital readmission in diabetics? or better yet, predict these events?