Abstract
Match-making systems refer to systems where users want toing need. Examples of match-making systems include datingbased question answering, and consumer-to-consumer marketmaking system is the retrieval and ranking of candidate mstudy of information retrieval approaches applied to matcfor a dating service. This domain offers several unique ptasks. These include two-sided relevance, very subjectivetured queries. We propose a machine learned ranking functuniquely rich user profiles that consist of both structurcarried out using data gathered from a real online datingogy with respect to traditional match-making baseline systhe aspects of match-making that are particularly importa