Prediction of stock price using an adaptive Neuro-Fuzzy Inference System trained by Firefly Algorithm

Nhu, Hien Nguyen; Nitsuwat, Supot; Sodanil, Maleerat

doi:10.1109/icsec.2013.6694798

Cited by 29 publications

(10 citation statements)

References 16 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the search of more effective training and optimization of ANFIS models, the researchers have explored the use of Firefly Algorithm (FA), Artificial Bee Colony (ABC), and Differential Evolution with Ant Colony Search (DEACS) algorithms [2], [24][25]. All of them were employed for both antecedent and consequent parameters learning.…”

Section: Training Methods Of Anfismentioning

confidence: 99%

“…The applications are found in stock market prediction, supply chain management, profit maximization, bankruptcy prediction of firms, electric load forecasting etc. [1][2]. Among other fuzzy systems, Adaptive Neuro-Fuzzy Inference System (ANFIS) is more frequently used technique since it is computationally less expensive, transparent, and produces results as robust as statistical models [3][4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Training Methods of ANFIS for Applications in Business and Economics

Salleh¹,

Hussain²

2016

IJUNESST

View full text Add to dashboard Cite

Fuzzy Neural Networks (FNNs) techniques have been effectively used in applications that range from medical to mechanical engineering, to business and economics. Despite of attracting researchers in recent years and outperforming other fuzzy systems, Adaptive Neuro-Fuzzy Inference System (ANFIS) still needs effective parameter training and rulebase optimization methods to perform efficiently when the number of inputs increase. Moreover, the standard gradient based learning via two pass learning algorithm is prone slow and prone to get stuck in local minima. Therefore many researchers have trained ANFIS parameters using metaheuristic algorithms however very few have considered optimizing the ANFIS rule-base. Mostly Particle Swarm Optimization (PSO) and its variants have been applied for training approaches used. Other than that, Genetic Algorithm (GA), Firefly Algorithm (FA), Ant Bee Colony (ABC) optimization methods have been employed for effective training of ANFIS networks when solving various problems in the field of business and finance.

show abstract

Section: Training Methods Of Anfismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Review of Training Methods of ANFIS for Applications in Business and Economics

Salleh¹,

Hussain²

2016

IJUNESST

View full text Add to dashboard Cite

show abstract

“…ANN capable of learning complex nonlinear relationships but difficult to finely model for human reasoning of logical process [45].…”

Section: Machine Learningmentioning

confidence: 99%

“…Fuzzy system have the insufficient learning ability and difficultly for its time consuming to determine for the correct set of parameters [54].…”

Section: Fuzzy Algorithmmentioning

confidence: 99%

Technical Approach in Text Mining for Stock Market Prediction: A Systematic Review

Islam

Alshaikhli

Nor

et al. 2018

IJEECS

View full text Add to dashboard Cite

Text mining methods and techniques have disclosed the mining task throughout information retrieval discipline in the field of soft computing techniques. To find the meaningful information from the vast amount of electronic textual data become a humongous task for trading decision. This empirical research of text mining role on financial text analysing in where stock predictive model need to improve based on rank search method. The review of this paper basically focused on text mining techniques, methods and principle component analysis that help reduce the dimensionality within the characteristics and optimal features. Moreover, most sophisticated soft-computing methods and techniques are reviewed in terms of analysis, comparison and evaluation for its performance based on electronic textual data. Due to research significance, this empirical research also highlights the limitation of different strategies and methods on exact aspects of theoretical framework for enhancing of performance.

show abstract

“…Particle Swarm Optimization (PSO) algorithms are efficient solvers in these optimization problems. Some recent approaches to the optimal tuning of fuzzy models by PSO algorithms include the heterogeneous multi-swarm PSO applied to the parameters suitable for the sub-spaces of T-S fuzzy models [14], the adaptive neuro-fuzzy inference systems for time series prediction [15], the fuzzy unit commitment problems solving in power systems [16], the optimal tuning of fuzzy relational models [17] and of fuzzy logic relocation models [18], and the optimal tuning of initial states of fuzzy cregression models by Euclidian PSO [19].…”

Section: Introductionmentioning

confidence: 99%

Particle Swarm Optimization of fuzzy models for Anti-Lock Braking Systems

Precup

Sabau

Dragoş

et al. 2014

2014 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)

View full text Add to dashboard Cite

This paper suggests a Particle Swarm Optimization (PSO) approach to the optimal tuning of fuzzy models for Antilock Braking Systems (ABSs). A set of ten local state-space models of the ABS is first obtained by the linearization of the nonlinear state-space model of the ABS process at ten operating points. The initial Takagi-Sugeno (T-S) fuzzy models are next obtained by the modal equivalence principle, namely by placing the local state-space models of the process in the rule consequents. The optimization problem targets the minimization of the objective function (OF) expressed as the mean squared modeling error, and the vector variable of the OF consists of the feet of the triangular input membership functions. A PSO algorithm solves the optimization problem and gives the optimal T-S fuzzy models. A set of real-time experimental results is included to validate the PSO approach and the optimal T-S fuzzy models for real-world ABS laboratory equipment.

show abstract

Prediction of stock price using an adaptive Neuro-Fuzzy Inference System trained by Firefly Algorithm

Cited by 29 publications

References 16 publications

A Review of Training Methods of ANFIS for Applications in Business and Economics

A Review of Training Methods of ANFIS for Applications in Business and Economics

Technical Approach in Text Mining for Stock Market Prediction: A Systematic Review

Particle Swarm Optimization of fuzzy models for Anti-Lock Braking Systems

Contact Info

Product

Resources

About