Collaborative filtering in sequential and distributed platform.
Used Apache Spark to handle large Amazon datasets (233M reviews). Wrote Python and SQL scripts to parse and import data into MySQL. Applied memory based (user and item based) and model based (SVD, ALS matrix factorization) collaborative filtering methods. Harnessed fast cloud computing environment on AWS EC2.
Contributor: Joseph Patten, Scott Walters and Md Mahedi Hasan
