Using a Modified Trainable Neural Network Ensemble for Trend Prediction of Tehran Stock Exchange (Case Study: Kharg Petrochemical Company)

Subject Areas : Futurology

A.  Shahrabadi ¹ (ندارد)
R.  Ebrahimpour ² (ندارد)
H.  Nikoo ³ (نویسنده مسئول یا طرف مکاتبه)

Received: 2008-10-09 Accepted : 2008-11-27 Published : 2010-06-22

Keywords: Multi layered perceptrons (MLP, Trainable neural network ensem, Topology, Back&#x0D, &#x0D, propagation algorithm, Time series prediction,

Abstract :

This paper represents a comparison between modified trainable neural network ensemble with othertrainable and non-trainable ensembles. The historical data available in this case study are from khargpetrochemical company in Tehran stock exchange. This company is one of the biggest producers ofpetrochemicals, including methanol, in Iran and its stock price is very much dependent on worldmethanol price. Therefore Kharg stock price reflects its financial information more clearly than otherswith no products for global exportation. The reason of choosing Kharg is related to its large datahistory and high rate of stock free float1. The results show how a modified trainable neural networkensemble can overcome other trainable and non-trainable ensembles. This study also demonstrateshow we can beat the market through our proposed model without the use of extensive market data orknowledge