Optimal partition algorithm of the RBF neural network and its application to financial time series forecasting

Sun, Fang Hong; Liang, Cong; Zhang, L.; Lee, P.; Lin, Zhouchen; Cao, Jingchen

doi:10.1007/s00521-004-0439-7

Cited by 42 publications

(19 citation statements)

References 12 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Various ANN based methods like Multi Layer Perception Network (MLP) [6], Radial Basis Function Neural Network (RBF) [7], Wavelet Neural Network (WNN) [8] , Recurrent Neural Network (RNN) [9] and Functional Link Artificial Neural Network (FLANN) [10][11][12][13] are extensively used for stock market prediction due to their inherent capabilities to identify complex nonlinear relationship present in the time series data based on historical data and to approximate any nonlinear function to a high degree of accuracy. A major benefit of neural networks is that it incorporates prior knowledge in ANN to improve the performance of stock market prediction.…”

Section: Co-published By Atlantis Press and Taylor And Francismentioning

confidence: 99%

Polynomial Based Functional Link Artificial Recurrent Neural Network adaptive System for predicting Indian Stocks

Bebarta¹,

Biswal²,

Dash³

2015

IJCIS

View full text Add to dashboard Cite

A low complexity Polynomial Functional link Artificial Recurrent Neural Network (PFLARNN) has been proposed for the prediction of financial time series data. Although different types of polynomial functions have been used for low complexity neural network architectures earlier for stock market prediction, a comparative study is needed to choose the optimal combinations of the nonlinear functions for a reasonably accurate forecast. Further a recurrent version of the Functional link neural network is used to model more accurately a chaotic time series like stock market indices with a lesser number of nonlinear basis functions. The proposed PFLARNN model when trained with the well known gradient descent algorithm produces reasonable accuracy with a choice of range of weight parameters of the network. However, to improve the accuracy of the forecast further, the weight parameters of the recurrent functional neural network are optimized using an evolutionary learning algorithm like the differential evolution (DE). A comparison with other well known neural architectures shows that the proposed low complexity neural model can provide significant prediction accuracy for one day advance and speed of convergence using the International Business Machines Corp. (IBM) stock market indices.

show abstract

Section: Co-published By Atlantis Press and Taylor And Francismentioning

confidence: 99%

Polynomial Based Functional Link Artificial Recurrent Neural Network adaptive System for predicting Indian Stocks

Bebarta¹,

Biswal²,

Dash³

2015

IJCIS

View full text Add to dashboard Cite

show abstract

“…Among other neural network models; Radial Basis Function Neural Network (RBFNN) [21][22][23], Local Linear Radial Basis Function Neural Network (LLRBFNN) [24], Wavelet Neural Network (WNN) [25], Local Linear Wavelet Neural Network (LLWNN) [26][27], Recurrent Neural Network (RNN) [28][29], are widely used in time series prediction. Further to meet the increasing needs for better forecasting models; several nonlinear models have been developed by researchers.…”

Section: Introductionmentioning

confidence: 99%

Times Series Forecasting using Chebyshev Functions based Locally Recurrent neuro-Fuzzy Information System

Parida¹,

Bisoi²,

Dash³

et al. 2017

IJCIS

View full text Add to dashboard Cite

The model proposed in this paper, is a hybridization of fuzzy neural network (FNN) and a functional link neural system for time series data prediction. The TSK-type feedforward fuzzy neural network does not take the full advantage of the use of the fuzzy rule base in accurate input-output mapping and hence a hybrid model is developed using the Chebyshev polynomial functions to construct the consequent part of the fuzzy rules. The model to be known as locally recurrent neuro fuzzy information system (LRNFIS) is used to provide an expanded nonlinear transformation to the input space thereby increasing its dimension which will be adequate to capture the nonlinearities and chaotic variations in the time series. The locally recurrent nodes will provide feedback connections between outputs and inputs allowing signal flow in both forward and backward directions, giving the network a dynamic memory useful to mimic dynamic systems. For training the proposed LRNFIS, an improved firefly-harmony search (IFFHS) learning algorithm is used to estimate the parameters of the consequent part and feedback loop parameters. Three real world time series databases like the electricity price of PJM electricity market, the widely studied currency exchange rates between US Dollar (USD) and other four currencies i.e. Australian Dollar (AUD), Swiss Franc (CHF), Mexican Peso (MXN), Brazilian Real (BRL), along with S&P 500 and Nikkei 225 stock market data are used for performance validation of the newly proposed LRNFIS.

show abstract

“…Some of these astute computational methods include artificial neural networks (ANN), support vector machines (SVM) and fuzzy logic systems [1]. ANNs variants include the radial basis function neural network RBFNN [2], recurrent neural network RNN [3], multilayer perceptron MLP [4], generalized regression neural networks GRNN [5], random vector functional link neural network FLANN [6], local linear wavelet neural network LLWNN [7] and wavelet neural network WNN [8]. These neural network designs, nonetheless, cannot show strong performance owing to the volatile and multidimensional character of the dataset coupled which is coupled with noise, as well.…”

Section: Introduction and Literature Reviewmentioning

confidence: 99%

Effects of Technical Market Indicators on Stock Market Index Direction Forecasting

Şenyurt¹,

Subaşı²

2015

Modeling of Artificial Intelligence

View full text Add to dashboard Cite

In this study, we examine and compare the performances of data mining techniques based on the daily indexes of five different markets, namely DAX, FTSE 100, NASDAQ Composite, NIKKEI 225 and NYSE Composite. The A/D oscillator, chaikin oscillator, moving average convergence/divergence, stochastic oscillator, acceleration, momentum, chaikin volatility, fast stochastics, slow stochastics, williams %R, negative volume index, positive volume index, relative strength index, accumulation/distribution line, bollinger band, highest high, lowest low, median price, on balance volume, price rate of change, price-volume trend, typical price, volume rate of change, weighted close and williams accumulation/distribution make up the 28 technical indicator attributes used in this study. The data mining techniques utilized in this study comprise of random forest model, artificial neural network (ANN) and support vector machine (SVM). Initially, the input features are sorted with WEKA's Info Ranker which reveals the best attributes based on relative weight. Afterwards, ten attributes having the highest relative weight values are fed into random forest, ANN and SVM. Then different attribute combinations based on their relative weights are tested in turns for more precision.

show abstract

Optimal partition algorithm of the RBF neural network and its application to financial time series forecasting

Cited by 42 publications

References 12 publications

Polynomial Based Functional Link Artificial Recurrent Neural Network adaptive System for predicting Indian Stocks

Polynomial Based Functional Link Artificial Recurrent Neural Network adaptive System for predicting Indian Stocks

Times Series Forecasting using Chebyshev Functions based Locally Recurrent neuro-Fuzzy Information System

Effects of Technical Market Indicators on Stock Market Index Direction Forecasting

Contact Info

Product

Resources

About