Performance Analysis of MLPFF Neural Network Back Propagation Training Algorithms for Time Series Data

Author

Kumar, D. Arun ; Murugan, S.

Author_Institution

Dept. of Comput. Sci., Gov. Arts Coll., Tiruchirappalli, India

fYear

2014

fDate

Feb. 27 2014-March 1 2014

Firstpage

114

Lastpage

119

Abstract

This paper investigates the various training algorithm with Multi-Layer Perceptron Feed Forward Neural Network (MLPFFNN) and identify the best training algorithm for Indian Stock Exchange Market especially for BSE100 and NIFTY MIDCAP50. The forecasting accuracy is analyzed and measured with reference to an Indian stock market index such as Bombay Stock Exchange (BSE) and NIFTY MIDCAP50 in this study and it is found that the best training algorithm is Levenberg-Marquardt. All Training algorithms uses the 1-5-1 MLPFFNN architecture and its various parameter such as epochs, learning rate, etc are studied and the results are tabulated for the data division ratio 60%, 20% and 20% which represents training, validating and testing for all training algorithm.

Keywords

backpropagation; multilayer perceptrons; stock markets; time series; 1-5-1 MLPFFNN architecture; BSE; BSE100; Bombay stock exchange; Indian stock exchange market; Levenberg-Marquardt algorithm; MLPFF neural network backpropagation training algorithms; NIFTY MIDCAP50; data division ratio; epochs; learning rate; multilayer perceptron feed forward neural network; performance analysis; time series data; Algorithm design and analysis; Forecasting; Indexes; Neural networks; Prediction algorithms; Stock markets; Training; Neural Network; Time series; forecasting; stock market; training algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Computing and Communication Technologies (WCCCT), 2014 World Congress on

Conference_Location

Trichirappalli

Print_ISBN

978-1-4799-2876-7

Type

conf

DOI

10.1109/WCCCT.2014.47

Filename

6755117