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

  title={An Evolutionary Functional Link Neural Fuzzy Model for Financial Time Series Forecasting},
  author={Sreejit Chakravarty and Pradipta Kishore Dash and V. Ravikumar Pandi and Bijaya Ketan Panigrahi},
  journal={Int. J. Appl. Evol. Comput.},
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… 


This project analyzed various evolutiona ry computation algorithms for forecasting of financial data based on Adaptive Neuro Fuzzy Inference System and FLANN parameters updated by Least mean square and compared those using historical data from the stock exchanges.

Software Effort Estimation Using Functional Link Neural Networks Tuned with Active Learning and Optimized with Particle Swarm Optimization

The computational results show that the active learning along with PSO optimized FLANN greatly improves the performance of the model and its variants for software development effort estimation.

Evolutionary extreme learning machine for energy price forecasting

Experimental results show the superiority of the proposed E-ICSELM model when it is compared with simple ELM and Evolutionary-Cuckoo Search based ELM (ECSELM).

Hybrid Honey Bees Meta-Heuristic for Benchmark Data Classification

The experimental result shows that the proposed GABC-LM performs better than that standard BP, ABC, PSO, and GABC for the classification task.

Class Topper Optimization for the Problem of Portfolio Optimization with a Restricted Set of Assets

In this work, Class Topper Optimization (CTO) technique is used to provide a meta-heuristic strategy for portfolio optimization, and the mean-variance portfolio selection is the subject of the research.

Tests de l'efficience faible à partir des ondelettes de Haar

Cette these proposee utilise les ondelettes de Haar a creer de nouveaux indicateurs techniques, d’en evaluer leurs performances afin de tester la validite de l’efficience faible des marches



Evolutionary fuzzy neural networks for hybrid financial prediction

  • Lixin YuYanqing Zhang
  • Computer Science
    IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)
  • 2005
An evolutionary fuzzy neural network using fuzzy logic, neural networks, and genetic algorithms (GAs) is proposed for financial prediction with hybrid input data sets from different financial domains and results indicate that hybrid iterative evolutionary learning combining both GA and the gradient descent learning algorithm is more powerful than the previous separate sequential training algorithm.

Integration of an Improved Particle Swarm Algorithm and Fuzzy Neural Network for Shanghai Stock Market Prediction

  • Huang Fu-yuan
  • Computer Science
    2008 Workshop on Power Electronics and Intelligent Transportation System
  • 2008
An improved particle swarm optimization algorithm (IPSO) is developed and then combined with fuzzy neural network to optimize the network training process and it seems that the proposed new comprehensive evolution algorithm may be an efficient forecasting system in financial time series analysis.

A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm

  • R. Kuo
  • Computer Science
    Eur. J. Oper. Res.
  • 2001

PSO-based single multiplicative neuron model for time series prediction

Forecasting Stock Price Using a Genetic Fuzzy Neural Network

  • Huang Fu-yuan
  • Computer Science
    2008 International Conference on Computer Science and Information Technology
  • 2008
An integration of genetic algorithm and fuzzy neural networks (GFNN) are proposed to forecast stock price and the results indicate that the predictive accuracies obtained from GFNN are much higher than the ones obtained from NNs.

Neuro-Fuzzy Network Based On Extended Kalman Filtering for Financial Time Series

A novel Neuro-fuzzy architecture based on Extended Kalman filter is presented, which can be applied to an on-line incremental adaptive learning for the prediction of financial time series and is demonstrated to be a superior neuro- fuzzy modeling technique.