Fusion ANFIS model based on AR for forecasting EPS of leading industries

Liang Ying Wei, Ching Hsue Cheng, Hsin-Hung Wu

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Earnings per share (EPS) represents the profitability of a common stock and the financial performance of a particular company. Therefore, EPS is often regarded as a major indicator for investors to purchase stocks. The traditional approach is to use a conventional linear time series model for EPS prediction. However, the results would be in doubt when the forecasting problems are nonlinear. For this reason, this paper proposes a fusion forecasting model that incorporates an autoregressive model into an adaptive network-based fuzzy inference system (ANFIS) with three facets: (1) test the lag period of EPS; (2) take fuzzy inference systems (FIS) to fuzzify the past periods of EPS based on the AR concept and use adaptive networks to tune optimal parameters; and (3) employ an integrated ANFIS model to predict EPS. To illustrate the proposed model, 15-quarter EPS data are employed. The experimental results indicate that the proposed model outperforms the listing models.

Original languageEnglish
Pages (from-to)5445-5458
Number of pages14
JournalInternational Journal of Innovative Computing, Information and Control
Volume7
Issue number9
Publication statusPublished - 2011 Sep 1

Fingerprint

Fuzzy Inference System
Fuzzy inference
Forecasting
Fusion
Fusion reactions
Industry
Model-based
Model
Profitability
Time Series Models
Optimal Parameter
Autoregressive Model
Facet
Linear Time
Linear Model
Predict
Time series
Prediction
Experimental Results

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Computational Theory and Mathematics

Cite this

@article{ddbe56985e1a4debb4c43a7efefd284e,
title = "Fusion ANFIS model based on AR for forecasting EPS of leading industries",
abstract = "Earnings per share (EPS) represents the profitability of a common stock and the financial performance of a particular company. Therefore, EPS is often regarded as a major indicator for investors to purchase stocks. The traditional approach is to use a conventional linear time series model for EPS prediction. However, the results would be in doubt when the forecasting problems are nonlinear. For this reason, this paper proposes a fusion forecasting model that incorporates an autoregressive model into an adaptive network-based fuzzy inference system (ANFIS) with three facets: (1) test the lag period of EPS; (2) take fuzzy inference systems (FIS) to fuzzify the past periods of EPS based on the AR concept and use adaptive networks to tune optimal parameters; and (3) employ an integrated ANFIS model to predict EPS. To illustrate the proposed model, 15-quarter EPS data are employed. The experimental results indicate that the proposed model outperforms the listing models.",
author = "Wei, {Liang Ying} and Cheng, {Ching Hsue} and Hsin-Hung Wu",
year = "2011",
month = "9",
day = "1",
language = "English",
volume = "7",
pages = "5445--5458",
journal = "International Journal of Innovative Computing, Information and Control",
issn = "1349-4198",
publisher = "IJICIC Editorial Office",
number = "9",

}

Fusion ANFIS model based on AR for forecasting EPS of leading industries. / Wei, Liang Ying; Cheng, Ching Hsue; Wu, Hsin-Hung.

In: International Journal of Innovative Computing, Information and Control, Vol. 7, No. 9, 01.09.2011, p. 5445-5458.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fusion ANFIS model based on AR for forecasting EPS of leading industries

AU - Wei, Liang Ying

AU - Cheng, Ching Hsue

AU - Wu, Hsin-Hung

PY - 2011/9/1

Y1 - 2011/9/1

N2 - Earnings per share (EPS) represents the profitability of a common stock and the financial performance of a particular company. Therefore, EPS is often regarded as a major indicator for investors to purchase stocks. The traditional approach is to use a conventional linear time series model for EPS prediction. However, the results would be in doubt when the forecasting problems are nonlinear. For this reason, this paper proposes a fusion forecasting model that incorporates an autoregressive model into an adaptive network-based fuzzy inference system (ANFIS) with three facets: (1) test the lag period of EPS; (2) take fuzzy inference systems (FIS) to fuzzify the past periods of EPS based on the AR concept and use adaptive networks to tune optimal parameters; and (3) employ an integrated ANFIS model to predict EPS. To illustrate the proposed model, 15-quarter EPS data are employed. The experimental results indicate that the proposed model outperforms the listing models.

AB - Earnings per share (EPS) represents the profitability of a common stock and the financial performance of a particular company. Therefore, EPS is often regarded as a major indicator for investors to purchase stocks. The traditional approach is to use a conventional linear time series model for EPS prediction. However, the results would be in doubt when the forecasting problems are nonlinear. For this reason, this paper proposes a fusion forecasting model that incorporates an autoregressive model into an adaptive network-based fuzzy inference system (ANFIS) with three facets: (1) test the lag period of EPS; (2) take fuzzy inference systems (FIS) to fuzzify the past periods of EPS based on the AR concept and use adaptive networks to tune optimal parameters; and (3) employ an integrated ANFIS model to predict EPS. To illustrate the proposed model, 15-quarter EPS data are employed. The experimental results indicate that the proposed model outperforms the listing models.

UR - http://www.scopus.com/inward/record.url?scp=80052480851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052480851&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:80052480851

VL - 7

SP - 5445

EP - 5458

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

SN - 1349-4198

IS - 9

ER -