Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks

Forecasting earnings per share (EPS) are among the most important and crucial tasks for both outside investors and internal managers. The focus of most articles in literature is forecasting EPS with linear methods. Researchers rarely employ nonlinear models to forecast EPS. However some researchers...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sajad Naghdi, Mohammad Arab Mazar Yazdi (Ph.D)
Formato:	article
Lenguaje:	FA
Publicado:	Shahid Bahonar University of Kerman 2017
Materias:	earnings per share forecasting artificial neural network genetic algorithm Accounting. Bookkeeping HF5601-5689
Acceso en línea:	https://doaj.org/article/9bae08e4e525460787f5b4a6d451c73a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9bae08e4e525460787f5b4a6d451c73a
record_format	dspace
spelling	oai:doaj.org-article:9bae08e4e525460787f5b4a6d451c73a2021-11-04T19:53:13ZForecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks2008-89142476-292X10.22103/jak.2017.7086.2051https://doaj.org/article/9bae08e4e525460787f5b4a6d451c73a2017-11-01T00:00:00Zhttps://jak.uk.ac.ir/article_1757_4e342a267103f7c4c72dd54d1622c6e7.pdfhttps://doaj.org/toc/2008-8914https://doaj.org/toc/2476-292XForecasting earnings per share (EPS) are among the most important and crucial tasks for both outside investors and internal managers. The focus of most articles in literature is forecasting EPS with linear methods. Researchers rarely employ nonlinear models to forecast EPS. However some researchers show that nonlinearities exist in the relation between EPS and its determinants. This finding of nonlinearities provides support for the use of non-linear models in the field of earnings per share.In this paper, the model based on an Artificial Neural Network (ANN) to predict EPS is proposed. After that, ANN model was optimized by Genetic Algorithm and particle swarm optimization. The Genetic Algorithm and particle swarm optimizations used to select the most relevant input variables because selection of input variables is a key stage in building predictive models, In this paper, The Genetic Algorithm and particle swarm optimizations used to select the effective variables on the EPS using a sample of 131 companies listed in the Tehran Stock Exchange through for the years 1389_1391.The results reveals that the genetic algorithm and swarm optimization is able to extract the effective variables on the EPS amongst the factors affecting EPS, and also have been caused improve power capabilities and expansion of neural network structure.Sajad NaghdiMohammad Arab Mazar Yazdi (Ph.D)Shahid Bahonar University of Kermanarticleearnings per share forecastingartificial neural networkgenetic algorithmAccounting. BookkeepingHF5601-5689FAمجله دانش حسابداری, Vol 8, Iss 3, Pp 7-34 (2017)
institution	DOAJ
collection	DOAJ
language	FA
topic	earnings per share forecasting artificial neural network genetic algorithm Accounting. Bookkeeping HF5601-5689
spellingShingle	earnings per share forecasting artificial neural network genetic algorithm Accounting. Bookkeeping HF5601-5689 Sajad Naghdi Mohammad Arab Mazar Yazdi (Ph.D) Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks
description	Forecasting earnings per share (EPS) are among the most important and crucial tasks for both outside investors and internal managers. The focus of most articles in literature is forecasting EPS with linear methods. Researchers rarely employ nonlinear models to forecast EPS. However some researchers show that nonlinearities exist in the relation between EPS and its determinants. This finding of nonlinearities provides support for the use of non-linear models in the field of earnings per share.In this paper, the model based on an Artificial Neural Network (ANN) to predict EPS is proposed. After that, ANN model was optimized by Genetic Algorithm and particle swarm optimization. The Genetic Algorithm and particle swarm optimizations used to select the most relevant input variables because selection of input variables is a key stage in building predictive models, In this paper, The Genetic Algorithm and particle swarm optimizations used to select the effective variables on the EPS using a sample of 131 companies listed in the Tehran Stock Exchange through for the years 1389_1391.The results reveals that the genetic algorithm and swarm optimization is able to extract the effective variables on the EPS amongst the factors affecting EPS, and also have been caused improve power capabilities and expansion of neural network structure.
format	article
author	Sajad Naghdi Mohammad Arab Mazar Yazdi (Ph.D)
author_facet	Sajad Naghdi Mohammad Arab Mazar Yazdi (Ph.D)
author_sort	Sajad Naghdi
title	Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks
title_short	Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks
title_full	Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks
title_fullStr	Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks
title_full_unstemmed	Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks
title_sort	forecasting eps o with hybrid genetic algorithm, particle swarm optimization and neural networks
publisher	Shahid Bahonar University of Kerman
publishDate	2017
url	https://doaj.org/article/9bae08e4e525460787f5b4a6d451c73a
work_keys_str_mv	AT sajadnaghdi forecastingepsowithhybridgeneticalgorithmparticleswarmoptimizationandneuralnetworks AT mohammadarabmazaryazdiphd forecastingepsowithhybridgeneticalgorithmparticleswarmoptimizationandneuralnetworks
_version_	1718444608001671168

Forecasting EPS o with Hybrid Genetic algorithm, particle swarm optimization and Neural networks

Ejemplares similares