论文信息 - Artificial Neural Networks Applied to an Agent Acting in CDA Auctions in TAC

Artificial Neural Networks Applied to an Agent Acting in CDA Auctions in TAC

This paper describes an approach based on Artificial Neural Networks to estimate the trading price of bids in CDA auctions in the TAC Classic scenario. To validate the approach, we used some methods to validate the performances of both the ANN and an agent which uses the approach. By analyzing the results of the experiments we could prove that such estimation helps improving the agent's performance.

[1] Heaton T. Jeff,et al. Introduction to Neural Networks with Java , 2005 .

[2] Rajarshi Das,et al. Agent-Human Interactions in the Continuous Double Auction , 2001, IJCAI.

[3] T. Ishida,et al. A Trading Agent Competition for the Research Community , 1999 .

[4] Simon Haykin,et al. Neural Networks: A Comprehensive Foundation , 1998 .

[5] Anderson da Silva Soares,et al. Predição de séries temporais econômicas por meio de redes neurais artificiais e transformada Wavelet: combinando modelo técnico e fundamentalista , 2008 .

[6] Mario Malcangi,et al. Language-independent, neural network-based, text-to-phones conversion , 2009, Neurocomputing.

[7] Po-Chang Ko,et al. Resource allocation neural network in portfolio selection , 2008, Expert Syst. Appl..

[8] Perukrishnen Vytelingum,et al. The structure and behaviour of the continuous double auction , 2006 .

[9] อนิรุธ สืบสิงห์,et al. Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[10] Athanasios Kehagias,et al. Predictive modular fuzzy systems for time-series classification , 1997, IEEE Trans. Fuzzy Syst..

[11] Jun Zhu,et al. A Distributed Computing Service for Neural Networks and Its Application to Flood Peak Forecasting , 2006, ICONIP.