Abstract
For financial time series, the generation of error bars on the point of prediction is important in order to estimate the corresponding risk. In recent years, optimization techniques-driven artificial intelligence has been used to make time series approaches more systematic and improve forecasting performance. This paper presents a local linear radial basis functional neural network (LLRBFNN) model for classifying finance data from Yahoo Inc. The LLRBFNN model is learned by using the hybrid technique of backpropagation and recursive least square algorithm. The LLRBFNN model uses a local linear model in between the hidden layer and the output layer in contrast to the weights connected from hidden layer to output layer in typical neural network models. The obtained prediction result is compared with multilayer perceptron and radial basis functional neural network with the parameters being trained by gradient descent learning method. The proposed technique provides a lower mean squared error and thus can be considered as superior to other models. The technique is also tested on linear data, i.e., diabetic data, to confirm the validity of the result obtained from the experiment.
Similar content being viewed by others
References
Chakravarty S, Dash PK (2009) Forecasting stock market indices using hybrid network. Nat Biol Inspir Comput. doi:10.1109/NABIC.2009.5393749 (ISBN 978-1-4244-5053-4/09/IEEE)
Majumdar M, Hussain MDA (2007) Forecasting of Indian stock market index using artificial neural network. Inf Sci 98–105
Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175
Wang J-H, Leu J-Y (1996) Stock market trend prediction using ARIMA-based neural networks. In: IEEE international conference on neural networks, 1996, vol 4. IEEE, pp 2160–2166
Liu H-C, Hung H-C (2010) Forecasting S&P-100 stock index volatility: the role of volatility asymmetry and distributional assumption in GARH models. Expert Syst Appl 37(7):4928–4934
Nekoukar V, Beheshti MTH (2010) A local linear radial basis function neural network for financial time series forecasting. Appl Intell 33(3):352–356. doi:10.1007/s10489-009-0171-1
Senapati MR, Das SP, Champati PK, Routray PK (2014) Local linear radial basis function neural networks for classification of breast cancer data. In: PISER 16, vol 02, pp 033–042
Carpinteiro OAS, Leite JPRR, Pinheiro CAM, Lima I (2012) Forecasting models for prediction in time series. Artif Intell Rev 38(2):163–171. doi:10.1007/s10462-011-9275-1
Senapati MR, Dash PK (2013) Intelligent system based on local linear wavelet neural network and recursive least square approach for breast cancer classification. Artif Intell Rev 39:151–163. doi:10.1007/s10462-011-9263-5
Li F, Li C (2009) Application study of BP neural network on stock market prediction. In: Ninth international conference on hybrid intelligent systems. IEEE, pp 174–177. doi:10.1109/HIS.2009.248
Hung JC (2011) Adaptive fuzzy-GARCH model applied to forecasting the volatility of stock markets using particle swarm optimization. Inf Sci. doi:10.1016/j.ins.2011.02.027
Shen W (2011) Forecasting stock indices using radial basis function neural networks optimized by artificial fish swarm algorithm. Knowl Based Syst 24(3):378–385. doi:10.1016/j.knosys.2010.11.001
Adebiyi AA, Ayo CK, Adebiyi MO, Otokiti SO (2012) An improved stock price prediction using hybrid market indicators. Afr J Comput ICT 5(5):124–135 (ISSN-2006-1781.IEEE)
Chen M-Y (2013) A hybrid ANFIS model for business failure prediction using PSO and subtractive clustering. Inf Sci 220:180–195. doi:10.1016/j.ins.2011.09.013
Samantray SR, Dash PK, Panda G (2006) Fault classification using HS-transformation and radial basis function neural network. Electr Power Syst Res 76:897–905
Bahrammizaee A (2010) A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert systems and hybrid intelligent system. Neural Comput Appl 19(8):1165–1195
Kawaji S, Chen YH (2001) Evolving neuro fuzzy system by hybrid soft computing approaches for system identification. Int J Adv Comput Intell Intell Inform 5(4):229–238
Senapati MR, Vijaya I, Dash PK (2007) Rule extraction from radial basis functional neural networks by using particle swarm optimization. J Comput Sci 3:592–599
Senapati MR, Panda G, Dash PK (2012) Hybrid approach using KPSO and RLS for RBFNN design for breast cancer detection. Neural Comput Appl. doi:10.1007/s00521-012-1286-6
Tomczak JM, Gonczarek A (2013) Decision rules extraction from data stream in the presence of changing context for diabetes treatment. Knowl Inf Syst 34(3):521–546
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Patra, A., Das, S., Mishra, S.N. et al. An adaptive local linear optimized radial basis functional neural network model for financial time series prediction. Neural Comput & Applic 28, 101–110 (2017). https://doi.org/10.1007/s00521-015-2039-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-015-2039-0