USC Melady Lab

Machine Learning for the real world


The USC Melady Lab develops machine learning and data mining algorithms for solving problems involving data with special structure, including time series, spatiotemporal data, and relational data. We work closely with domain experts to solve challenging problems and make significant impacts in computational biology, social media analysis, climate modeling, health care, and business intelligence.


Yan is offering the class CSCI-686 Advanced Data Analytics in the Spring 2014 semester.

Xinran received best technical poster during USC CS annual research review.

Dave will be working on mobile health sensing with Scott Sapponas at Microsoft Research Redmond in Summer 2014.

Yan gave a tutorial on Causality Analysis from Time Series Data at CIKM 2013.

Dave's paper on Accelerating Active Learning with Transfer Learning was accepted to ICDM 2013.

We built an online tool for visualizing Granger causal networks.

Yan received the 2013 Okawa Foundation Research Award.

The review of Yi's work is published on MIT tech review