Nowadays information available on the World Wide Web has reached unprecedented growth and it makes difficult for users to find the most relevant for them. In order to alleviate such issue, Recommender Systems (RSs) have been proposed to collect opinions and preferences about a set of items, process such preferences and build a personalized information access. While the most part of current RSs exploit centralized architecture to provide the service, in this manuscript we propose an alternative approach for building a general purpose RSs that provides to users with more transparent and decentralized rating strategy. Indeed, the proposed framework is built on top of a Distributed Ledger technology platform that runs without any centralized authority and it supports both decentralized ratings and ranking of different items. A preliminary evaluation on the Ethereum test network demonstrates the feasibility of the framework in terms of performance and cost.
A Smart Contract Based Recommender System
Lisi A.;De Salve A.;Mori P.;Ricci L.
2019-01-01
Abstract
Nowadays information available on the World Wide Web has reached unprecedented growth and it makes difficult for users to find the most relevant for them. In order to alleviate such issue, Recommender Systems (RSs) have been proposed to collect opinions and preferences about a set of items, process such preferences and build a personalized information access. While the most part of current RSs exploit centralized architecture to provide the service, in this manuscript we propose an alternative approach for building a general purpose RSs that provides to users with more transparent and decentralized rating strategy. Indeed, the proposed framework is built on top of a Distributed Ledger technology platform that runs without any centralized authority and it supports both decentralized ratings and ranking of different items. A preliminary evaluation on the Ethereum test network demonstrates the feasibility of the framework in terms of performance and cost.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.