Dimensionality reduction algorithms for improving efficiency of PromoRank: A comparison study

Abstract

© Springer International Publishing Switzerland 2015. It is often desirable to find markets or sale channels where an object, e.g., a product, person or service, can be recommended efficiently. Since the object may not be highly ranked in the global property space, PromoRank algorithm promotes a given object by discovering promotive subspace in which the target is top rank. However, the computation complexity of PromoRank is exponential to the dimension of the space. This paper studies the impact of dimensionality reduction algorithms, such as PCA or FA, in order to reduce the dimension size and, as a consequence, improve the performance of PromoRank. This paper evaluate multiple dimensionality reduction algorithms to obtains the understanding about the relationship between properties of data sets and algorithms such that an appropriate algorithm can be selected for a particular data set. The evaluation results show that dimensionality reduction algorithms can improve the performance of PromoRank while maintain an acceptable ranking accuracy.