Self Recommendation in peer to peer systems

Recommendation system aims to produce a set of significant and useful suggestions that can be meaningful for a particular user. This paper introduces a self-organizing algorithm that by exploiting of a decentralized strategy builds a distributed recommendation system. The available resources are represented by a string of bits namely describer. The describers are obtained by exploiting of a locality preserving hash function that maps similar resources into similar strings of bits. Each pear works independently with the aim to locate the similar describer in neighbor peers. The peer decisions are based on the application of ad-hoc probability functions. The outcome will be a fast recommendation service thanks to the emergent sorted overlay-network. Preliminaries experimental results show as the logical reorganization can improve the recommendation operations.