The Comparison of Neuro Fuzzy and Agent-based Simulation in Predicting Auction Price

• Main Authors: Shih-Min Weng, 翁士敏
• Other Authors: Chin-Shien Lin
• Format: Others
• Language: en_US
• Published: 2005
• Online Access: http://ndltd.ncl.edu.tw/handle/27008696027045301633

碩士 === 國立中興大學 === 電子商務研究所 === 93 === Online auction, being estimated to account for 25% electronic commerce by 2005, has now been a popular mechanism in setting price for internet users. However, auction price prediction, involving the modeling of uncertainty regarding the bidding process, is a challenging task primarily due to the variety of factors changing in auction settings. Even if all the factors were accounted for, there is still the uncertainty in human behavior when bidding in auctions. On any given day, there are more than 4 million items listed on Yahoo-Kimo Auction. These auctions are also producing large amounts of data that can be used to provide services to the buyers and sellers, market research, and product development. We collect historical auction data from Yahoo-Kimo Auction and use neuro Fuzzy technique and agent-based simulation to predict final selling prices of auction item. Using the Digital Camera category from Yahoo-Kimo Auction, we show that our methods are extremely accurate and they outperform traditional method and can be a great help for the buyers to avoid overpricing and for the sellers to facilitate the completion of the auction.