PROJECT TITLE :

Semiring Rank Matrix Factorisation - 2017

ABSTRACT:

Rank data, in that each row is a complete or partial ranking of obtainable items (columns), is ubiquitous. Among others, it can be used to represent preferences of users, levels of gene expression, and outcomes of sports events. It will have several varieties of patterns, among that consistent rankings of a subset of the items in multiple rows, and multiple rows that rank the identical subset of the items highly. In this article, we show that the problems of finding such patterns will be formulated among one generic framework that's based mostly on the concept of semiring matrix factorization. During this framework, we tend to employ the max-product semiring rather than the and-product semiring common in ancient linear algebra. We tend to apply this semiring matrix factorization framework on two tasks: sparse rank matrix factorization and rank matrix tiling. Experiments on both synthetic and globe datasets show that the framework is capable of discovering totally different types of structure along with obtaining prime quality solutions.