Price Forecasting Using Dynamic Assessment of Market Conditions and Agent's Bidding Behavior

Multiple online auctions need complex bidding decisions for selecting which auction to participate in, whether to place single or multiple bids, do early or late bidding and how much to bid. This paper designs a novel fuzzy dynamic bidding agent (FDBA) which uses a comprehensive method for initial price estimation and price forecasting. First, FDBA selects an auction to participate in and calculates its initial price based on clustering and bid selection approach. Then the price of the auction is forecasted based on the estimated initial price, attitude of the bidders to win the auction and the competition assessment for the late bidders using fuzzy reasoning technique. The experiments demonstrated improved price forecasting outcomes using the proposed approach.

[1]  Qian Chen,et al.  An Empirical Analysis of Bidding Behavior in Simultaneous Ascending-Bid Auctions , 2010, 2010 International Conference on E-Business and E-Government.

[2]  Alok Gupta,et al.  User heterogeneity and its impact on electronic auction market design: an empirical exploration , 2004 .

[3]  Jie Lu,et al.  Data mining driven agents for predicting online auction's end price , 2011, 2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[4]  Wolfgang Jank,et al.  An Automated and Data-Driven Bidding Strategy for Online Auctions , 2011, INFORMS J. Comput..

[5]  Pericles A. Mitkas,et al.  Efficient E-Commerce Agent Design Based on Clustering eBay Data , 2007, 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops.

[6]  Saroj Kaushik,et al.  Automated Fuzzy Bidding Strategy Using Agent's Attitude and Market Competition , 2009, PRIMA Workshops.

[7]  Jie Lu,et al.  Pricing Analysis in Online Auctions Using Clustering and Regression Tree Approach , 2011, ADMI.

[8]  Jaideep Srivastava,et al.  WEBKDD 2002 - Mining Web Data for Discovering Usage Patterns and Profiles , 2003, Lecture Notes in Computer Science.

[9]  GoesPaulo,et al.  User heterogeneity and its impact on electronic auction market design , 2004 .

[10]  James S. Fishkin,et al.  An Empirical Exploration , 1984 .

[11]  José M. Vidal,et al.  Agents on the Web: Online Auctions , 1999, IEEE Internet Comput..

[12]  Ashish Sureka,et al.  Mining eBay: Bidding Strategies and Shill Detection , 2002, WEBKDD.

[13]  Naoki Fukuta,et al.  Advances in Practical Multi-Agent Systems, PRIMA 2009 Workshops, Nagoya, Japan, December 14-16, 2009 , 2011, PRIMA Workshops.

[14]  Eric T. Bradlow,et al.  An Integrated Model for Bidding Behavior in Internet Auctions: Whether, Who, When, and how Much , 2005 .

[15]  Peter Stone,et al.  Autonomous Bidding Agents in the Trading Agent Competition , 2001, IEEE Internet Comput..