Detecting multiple seller collusive shill bidding

Shill bidding occurs when fake bids are introduced into an auction on the seller’s behalf in to artificially inflate final price. The seller either has associates bid auctions, or controls multiple bidder accounts that used for shill bidding. We proposed a reputation system referred as Score indicates how likely is be engaging price inflating behaviour specific auctions. A potential can observe other bidders’ Scores, and if they high, elect not participate there some evidence However, collusion with sellers, accounts, spread risk between various sellers reduce suspicion bidder. Collusive impacts one of characteristics examines; consequently, collusive bidder’s Score. This paper extends detect where working each other. propose first algorithm provide whether groups colluding. Based tight association level apparent occurring suspect adjusted appropriately remove any advantage from collusion. Performance demonstrated using simulated commercial data extensive experimental results presented.