FLANN Based Forecasting of S&amp;P 500 Index

Majhi, Banshidhar; Shalabi, Hasan; Fathi, Mowafak

doi:10.3923/itj.2005.289.292

Cited by 17 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Functional Link ANN (FLANN) having a single neuron and single layer architecture has been proposed. In general the functional link based neural network models were single-layer ANN structure possessing higher rate of convergence and lesser computational load than those of a MLP structure (Majhi, Shalabi, & Fathi, 2005;Chakravarty, & Dash, 2009). The mathematical expression and computational calculation is evaluated as per MLP.…”

Section: Literature Reviewmentioning

confidence: 99%

Prediction of Financial Time Series Data using Hybrid Evolutionary Legendre Neural Network

Dash

2016

International Journal of Applied Evolutionary Computation

View full text Add to dashboard Cite

In this paper a predictor model using Legendre Neural Network is proposed for one day ahead prediction of financial time series data. The Legendre Neural Network (LENN) is a single layer structure that possess faster convergence rate and reduced computational complexity by increasing the dimensionality of the input pattern with a set of linearly independent nonlinear functions. The parameters of the LENN model are estimated using a Moderate Random Search Particle Swarm Optimization Method (HMRPSO). The HMRPSO is a variant of PSO that uses a moderate random search method to enhance the global search ability of particles and increases their convergence rates by focusing on valuable search space regions. Training LENN using HMRPSO has also been compared with Particle Swarm Optimization (PSO) and Differential Evolution (DE) based learning of LENN for predicting the Bombay Stock Exchange and S&P 500 data sets.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Prediction of Financial Time Series Data using Hybrid Evolutionary Legendre Neural Network

Dash

2016

International Journal of Applied Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…First, we discard the LO σ ×Br(eµ) of Equation 5.2 in favor of NLO values provided to us by Choudhury et. al [64]. Second, we adopt an approach in which every event in data and MC respectively contributes to the N i obs and N i exp at each of the ∼ 600 M eµ points in the scan.…”

Section: Sensitivitymentioning

confidence: 99%

Search for high-mass resonances decaying to eμ in p$\bar{p}$ collisions at √s = 1.96 TeV

Hahn

2006

View full text Add to dashboard Cite

my supervisor, for his faith in me and for guiding my transition from engineering student to physicist. Prof. Peter Wittich, for his friendship, instruction and encouragement. Prof. Joe Kroll, for pushing me when my enthusiasm had flagged. Prof. Brig Williams, for allowing me an opportunity to experience an ATLAS test-beam before I entered graduate school. Dr. Ted Liu, for providing me freedom and encouragement in my work on the CDF Level 2 (PULSAR) Trigger upgrade. All in the Penn HEP group, for kindling my interest in hardware and computing.And, of course, Seema, my fiancee, for her love, support and patience.

show abstract

“…Fu-yuan (2008b) has adopted a combination of improved PSO algorithm and fuzzy neural network to predict Shanghai stock market indices and genetic fuzzy neural network (Fu-yuan, 2008a) to forecast Shhenzhen stock indices. Kuo has applied neural fuzzy model (Kuo, 2001) to forecast sales data of well known convenience store franchise company in Taiwan where weights are generated by GA. Functional link neural network (FLANN), an improved ANN, is used (Majhi, Shalabi, & Fathi, 2005) to predict S&P 500 stock. Recently, the same FLANN model when combined with recursive least square (RLS) algorithm produces better result in stock market predictions.…”

Section: Introductionmentioning

confidence: 99%

An Evolutionary Functional Link Neural Fuzzy Model for Financial Time Series Forecasting

Chakravarty¹,

Dash

Pandi

et al. 2011

International Journal of Applied Evolutionary Computation

View full text Add to dashboard Cite

This paper proposes a hybrid model, evolutionary functional link neural fuzzy model (EFLNF), to forecast financial time series where the parameters are optimized by two most efficient evolutionary algorithms: (a) genetic algorithm (GA) and (b) particle swarm optimization (PSO). When the periodicity is just one day, PSO produces a better result than that of GA. But the gap in the performance between them increases as periodicity increases. The convergence speed is also better in case of PSO for one week and one month a head prediction. To testify the superiority of the EFLNF, a number of comparative studies have been made. First, functional link artificial neural network (FLANN) and functional link neural fuzzy (FLNF) were combined with back propagation (BP) learning algorithm. The result shows that FLNF performs better than FLANN. Again, FLNF is compared with EFLNF where the latter outperforms the former irrespective of the periodicity or the learning algorithms with which it has been combined. All models are used to predict the most chaotic financial time series data; BSE Sensex and S&P CNX Nifty stock indices one day, one week and one month in advance.

show abstract

FLANN Based Forecasting of S&P 500 Index

Cited by 17 publications

References 4 publications

Prediction of Financial Time Series Data using Hybrid Evolutionary Legendre Neural Network

Prediction of Financial Time Series Data using Hybrid Evolutionary Legendre Neural Network

Search for high-mass resonances decaying to eμ in p$\bar{p}$ collisions at √s = 1.96 TeV

An Evolutionary Functional Link Neural Fuzzy Model for Financial Time Series Forecasting

Contact Info

Product

Resources

About