An Agent-based Method for Predicting Monthly Maximum & Minimum Quote Prices
عنوان مقاله: An Agent-based Method for Predicting Monthly Maximum & Minimum Quote Prices
شناسه ملی مقاله: IDMC01_017
منتشر شده در اولین کنفرانس داده کاوی ایران در سال 1386
شناسه ملی مقاله: IDMC01_017
منتشر شده در اولین کنفرانس داده کاوی ایران در سال 1386
مشخصات نویسندگان مقاله:
Helga Mazyar - Department of Electrical and Computer Engineering, Isfahan University of Technology Isfahan Mathematics House, Isfahan, Iran
Kaveh Mahdaviani - Department of Electrical and Computer Engineering, Isfahan University of Technology Isfahan Mathematics House, Isfahan, Iran
Saeed Majidi - Department of Electrical and Computer Engineering, Isfahan University of Technology Isfahan Mathematics House, Isfahan, Iran
Mohammad Saraee - Department of Electrical and Computer Engineering, Isfahan University of Technology Isfahan Mathematics House, Isfahan, Iran
خلاصه مقاله:
Helga Mazyar - Department of Electrical and Computer Engineering, Isfahan University of Technology Isfahan Mathematics House, Isfahan, Iran
Kaveh Mahdaviani - Department of Electrical and Computer Engineering, Isfahan University of Technology Isfahan Mathematics House, Isfahan, Iran
Saeed Majidi - Department of Electrical and Computer Engineering, Isfahan University of Technology Isfahan Mathematics House, Isfahan, Iran
Mohammad Saraee - Department of Electrical and Computer Engineering, Isfahan University of Technology Isfahan Mathematics House, Isfahan, Iran
In this paper a multi agent model for predicting monthly maximum and minimum quote prices has been proposed. This model is based on the training of Elman neural networks and using particle swarm optimization for obtaining the best parameters of the neural networks. Also one method for reducing the effects of overfitting problem is suggested. This method averages the outputs of an ensemble network, given noisy data as inout, to predict the final results.. Finally the results of using this model on a sample data set are presented and the effectiveness of this model is illustrated.
کلمات کلیدی: stock prediction, recurrent neural network, Particle Swarm Optimization, ensemble averaging
صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/32994/