Correlation Based ADALINE Neural Network for Commodity Trading | Science Publications

Journal of Computer Science

M. Nachamai¹  Anitha S. Pillai¹  J. Chandra¹ 

关键词: Return on Investments (ROI);    Artificial Neural Network (ANN);    Multilayer Perceptron (MLP);    Adaptive Linear Neuron (ADALINE);    Correlation Based Feature Selection (CBFS);    Mean of Magnitude Relative Error (MMRE);   

DOI  :  10.3844/jcssp.2015.863.871

学科分类：计算机科学（综合）

来源: Science Publications

【 摘 要 】

Commoditytrading is one of the most popular resources owning to its eminent predictablereturn on investment to earn money through trading. The trading includes allkinds of commodities like agricultural goods such as wheat, coffee, cocoa etc.and hard products like gold, rubber, crude oils etc.,. The investment decisioncan be made very easily with the help of the proposed model. The proposed modelcorrelation based multi layer perceptron feed forward adaline neural network isan integrated method to forecast the future values of all commodity trading.The correlation based adaline neuron is used as an optimized predictor in themulti layer perceptron feed forward neural network. The correlation is used forfeature selection before building the predictive model. The aim of the paper isto build the predictive model for commodity trading. The model is created usingcorrelation based feature selection and adaline neural network to prognosticateall future values of commodities. The adaptive linear neuron is formed with thehelp of linear regression. To implement the proposed model the live data iscaptured from mcxindia. The mcxindia is considered as one the popular websitefor doing commodities and derivatives in India. To train the proposed model,few random samples are used and the model is evaluated with the help of fewtest samples from the same data set.

【 授权许可】

Unknown