In this era of big data, it is difficult to know when a peculiar trend represents a true signal or an artifact. This project will search for the potential outliers amidst the many influenza vaccine studies that have been conducted to date. We will test whether odd trends hold across other studies and determine a "quality score" that quantifies our trust in each dataset.

Many studies have measured the response to vaccination, yet they often do so at different times. This project aims to unify these heterogeneous datasets by predicting each person's response at any time point that has been measured in any study. A basic level of programming is required. Expect to learn new techniques spanning from matrix completion to machine learning.