International Conference on Information Technology and Scientific Management (ICITSM 2010 E-BOOK)

Tianjin,China,12.20-12.21,2010

ISBN: 978-1-935068-40-2 Scientific Research Publishing, USA

E-Book 1078pp Pub. Date: December 2010

Category: Computer Science & Communications

Price: $220

Title: Weighted Functional K-Nearest Neighbor Method and Application in Close Price Prediction of Online Auction
Source: International Conference on Information Technology and Scientific Management (ICITSM 2010 E-BOOK) (pp 815-818)
Author(s): Zhoushanyue He, Dept. Mathematics, Beijing Normal University, Beijing, P. R. China
Abstract: A weighted functional K-nearest neighbor (weighted fKNN) method has been proposed to predict the close price of online auction based on the traditional fKNN. Weighted fKNN takes into account the difference between the distance measures, and generally produces better fit. A case study of the Ebay record of Palm M515 7-day auctions from March, 2003 to May, 2003 has been done, noting that the mean absolute prediction error is less than 5%, a better prediction than the traditional fKNN.
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top