The week's pick
Reseach Article
Inter-comparison of Artificial Neural Network Algorithms for Time Series Forecasting: Predicting Indian Financial Markets
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 162 - Number 2 |
| Year of Publication: 2017 |
| Authors: Shilpa Amit Verma, G. T. Thampi, Madhuri Rao |
10.5120/ijca2017913249
|
Shilpa Amit Verma, G. T. Thampi, Madhuri Rao . Inter-comparison of Artificial Neural Network Algorithms for Time Series Forecasting: Predicting Indian Financial Markets. International Journal of Computer Applications. 162, 2 ( Mar 2017), 1-13. DOI=10.5120/ijca2017913249
Abstract
The financial market prediction is a specialized case of a time series analysis. Although many different methods have been employed by researchers for time series/financial data studies which include statistical techniques like ANOVA (analysis of variances), ARIMA (integrated moving averages), smoothing methods, correlation analysis etc., use of Artificial Neural Network (ANN) methods for financial prediction have become quite popular in the recent times. Though ANN methods like the conventionally used backpropagation method or the recurrent methods have been employed in the past, a complete and detailed investigation of more robust and popular ANN methods incorporated into ANN like the Resilient backprop, Marquardt Lavenberg, Conjugate gradient methods, One Step Secant, Quasi Newton methods, Bayesian learning etc., is missing from the literature. In the present study, a detailed study was undertaken to investigate the potential of these robust methods in the ANN domain for the Indian financial market prediction, more specifically the prediction of the share price of two popular scripts that are traded in the Indian secondary market. In this study, the 1 month ahead opening share price of two scripts namely ICICI bank and L&T have been forecasted. The results of our study indicate that while as for L&T data, Marquardt Lavenberg algorithm is able to give ~85% accurate prediction, it gives ~92% accurate prediction for ICICI bank data. This study therefore attempts to conduct a detailed investigation of many popular methods under the ANN domain to converge on the best possible results instead of just considering one or two methods and comparing them to the backpropagation method-a method being followed conventionally.
References
- Hayan Mo, Jun Wang et al (2016) Exponent back propagation neural network forecasting for financial cross-correlation relationship. Expert Systems with applications 53: 106-116.
- K Hornik et al. (1989) Multilayer feedforward networks are universal approximators. Neural Networks 2: 359-366.
- VK Dhar et al. (2010) Comparative performance of some popular ANN algorithms on benchmark and function approximation problems. Pramana 74(2): 307-324.
- A. Victor Devadoss , T. Antony Alphonnse Ligori (2013) Stock Prediction Using Artificial Neural Networks. International Journal of Data Mining Techniques and Applications 2: 283-291.
- Yunus Yetis, Halid Kaplan, and Mo Jamshidi (2014) Stock Market Prediction by Using Artificial Neural Network. In Proc. World Automation Congress, U.S., 718-722. IEEE Computer Society. doi: 10.1109/WAC.2014.6936118
- G.Zhang, Time series forecasting using hybrid ARIMA-ANN models , NeuroComputing 50 (2003) 159-175.
- C Narendra Babu, B.Eshwara Reddy, A moving averages filter based ARIMA-ANN model forecasting time series data. ; Applied soft computing 23 (2014) 27-38.
- Jian Zhou Wang, Ju Zie Wang et al., Forecasting stock indices with backpropagation neural network, Expert systems with applications 38 (2011) 14346-14355.
- A S Chen, Leung M F, Application of Neural Networks for emerging financial markets , Computers and Operations Research 30 (2003) 901-923.
- Mingyue Qiu, Yusong et al., Application of ANN for prediction of stock market returns : Case of Japanese stock market; chaos, Solitions & Fractals 85 (2016) 1-7
- A H Moghaddam, M H Moghaddam et al., Journal of economics, finance & administrative Sience 21 (2016) 89-93.
- S N Sivanandam, S N Deepa, Principles of Soft computing 2nd Edition (2011) Wiley Publication.
- V.K. Dhar et al. (2013) Artificial Neural Network based gamma-hadron segregation methodology for TACTIC telescope. Nuclear Instruments and Methods in Physics Research A 708: 56–71.
- D.E. Rumelhart, et al. (1986) Learning representations by back-propagating errors. Nature 323: 533-536.
- M. Reidmiller (1994) Advanced supervised learning in multilayer perceptrons from backpropagation to adaptive learning algorithms. Computer Standards Interfaces 16: 265-278.
- M.F. Moller, et al. (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 6: 525-533.
- D.W. Marquardt(1963)An algorithm for least square estimation of non-linear parameters. Journal of the Society for Industrial and Applied Mathematics 11(2): 431-441
- www.nseindia.com
Index Terms
Keywords