Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction
Journal of Applied MathematicsPublished 1 January 2014Open access
Ayodele A. Adebiyi, Aderemi O. Adewumi, C. K. Ayo
Citations571
SJR quartileQ3
SJR score0.28
SNIP0.70
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper examines the forecasting performance of ARIMA and artificial neural networks model with published stock data obtained from New York Stock Exchange to reveal the superiority of Neural networks model over ARimA model.
Abstract
This paper examines the forecasting performance of ARIMA and artificial neural networks model with published stock data obtained from New York Stock Exchange. The empirical results obtained reveal the superiority of neural networks model over ARIMA model. The findings further resolve and clarify contradictory opinions reported in literature over the superiority of neural networks and ARIMA model and vice versa.
Keywords
Decision SciencesEngineering
International Journal of ForecastingForecasting with artificial neural networks:
4,162 Citations1998Guoqiang Zhang, B. Eddy Patuwo +1 more
A state-of-the-art survey of ANN applications in forecasting, a synthesis of published research, insights on ANN modeling issues, and the future research directions are presented.
Expert Systems with ApplicationsAn artificial neural network (p,d,q) model for timeseries forecasting
785 Citations2009Mehdi Khashei, Mehdi Bijari
The empirical results with three well-known real data sets indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by artificial neural networks, and can be used as an appropriate alternative model for forecasting task, especially when higher forecasting accuracy is needed.
Applied Soft ComputingHybrid neural network models for hydrologic time series forecasting
460 Citations2006Ashu Jain, Avadhnam Madhav Kumar
The results obtained in this study suggest that the approach of combining the strengths of the conventional and ANN techniques provides a robust modelling framework capable of capturing the non-linear nature of the complex time series and thus producing more accurate forecasts.
OmegaStock index forecasting based on a hybrid model
377 Citations2011Jujie Wang, Jianzhou Wang +2 more
Numerical results show that the proposed model outperforms all traditional models, including ESM, ARIMA, BPNN, the equal weight hybrid model (EWH), and the random walk model (RWM).
Knowledge-Based SystemsIntegration of genetic fuzzy systems and artificial neural networks for stock price forecasting
372 Citations2010Esmaeil Hadavandi, Hassan Shavandi +1 more
Results show that the proposed approach outperforms all previous methods, so it can be considered as a suitable tool for stock price forecasting problems.
Expert Systems with ApplicationsForecasting stock market short-term trends using a neuro-fuzzy based methodology
297 Citations2009George S. Atsalakis, Kimon P. Valavanis
Real case studies using data from emerging and well developed stock markets to train and evaluate the proposed neuro-fuzzy system illustrate that compared to the ''buy and hold'' strategy and several other reported methods, the proposed approach and the forecasting trade accuracy are by far superior.
Information SciencesTime-series forecasting using flexible neural tree model
294 Citations2004Yuehui Chen, Bo Yang +2 more
This paper introduces a new time-series forecasting model based on the flexible neural tree (FNT), which is generated initially as a flexible multi-layer feed-forward neural network and evolved using an evolutionary procedure.
NeurocomputingImprovement of Auto-Regressive Integrated Moving Average models using Fuzzy logic and Artificial Neural Networks (ANNs)
292 Citations2008Mehdi Khashei, Mehdi Bijari +1 more
Empirical results of financial markets forecasting indicate that the hybrid models exhibit effectively improved forecasting accuracy so that the model proposed can be used as an alternative to financial market forecasting tools.
Expert Systems with ApplicationsForecasting the volatility of stock price index
224 Citations2006Tae Hyup Roh
This model demonstrates the utility of the neural network forecasting combined with time series analysis for the financial goods in forecasting the volatility of stock price index in two view points: deviation and direction.
European Journal of Operational ResearchComparison of neural network models with ARIMA and regression models for prediction of Houston's daily maximum ozone concentrations
210 Citations2000Victor R. Prybutok, Junsub Yi +1 more
A neural network model for forecasting daily maximum ozone levels is developed and compared with two conventional statistical models, regression and Box–Jenkins ARIMA.
Expert Systems with ApplicationsA neural network-based fuzzy time series model to improve forecasting
209 Citations2009Tiffany Hui‐Kuang Yu, Kun‐Huang Huarng
Out-of-sample forecasting of the stock index in Taiwan is performed and the results are compared with those of previous studies to demonstrate the performance of the proposed model.
International Journal of Theoretical and Applied FinanceNEURAL NETWORKS FOR TECHNICAL ANALYSIS: A STUDY ON KLCI
193 Citations1999JingTao Yao, Chew Lim Tan +1 more
The results show that the neural network model can get better returns compared with conventional ARIMA models and the experiment also shows that useful predictions can be made without the use of extensive market data or knowledge.
Expert Systems with ApplicationsForecasting stock exchange movements using neural networks: Empirical evidence from Kuwait
146 Citations2010Mohamed M. Mostafa
The results of this study show that neuro-computational models are useful tools in forecasting stock exchange movements in emerging markets and indicate that the quasi-Newton training algorithm produces less forecasting errors compared to other training algorithms.
Expert Systems with ApplicationsAn empirical methodology for developing stockmarket trading systems using artificial neural networks
145 Citations2008Bruce Vanstone, Gavin Finnie
The key steps involved in creating a neural network for use in stockmarket trading are described, and particular emphasis is placed on designing these steps to suit the real-world constraints the neural network will eventually operate in.
Computational IntelligenceTime Series Prediction With Genetic‐Algorithm Designed Neural Networks: An Empirical Comparison With Modern Statistical Models
134 Citations1999James V. Hansen, James B. McDonald +1 more
Neural networks whose architecture is determined by genetic algorithms outperform autoregressive integrated moving average forecasting models in six different time series examples and give evidence of detecting patterns in data which remain hidden to the autoregression and moving average models.
Engineering Applications of Artificial IntelligenceDesign and implementation of NN5 for Hong Kong stock price forecasting
84 Citations2006Philip Tsang, P.C.K. Kwok +7 more
An attempt to build a stock buying/selling alert system using a backpropagation NN, NN5, is presented, and a best strategy for trading non-volatile stock like HSBC is recommended.
Research Technical PapersForecasting irish inflation using ARIMA models
76 Citations1998Geoff Kenny, Aidan Meyler +1 more
Computational Statistics & Data AnalysisForecasting nonlinear time series with neural network sieve bootstrap
72 Citations2006Francesco Giordano, Michele La Rocca +1 more
A new method to construct nonparametric prediction intervals for nonlinear time series data is proposed, which is model-free within a general class of nonlinear processes and avoids the specification of a finite dimensional model for the data generating process.
International Business ResearchCase Study of Factors Influencing Jobs Satisfaction in Two Malaysian Universities
50 Citations2009Edward Sek Khin Wong, Teoh Ngee Heng
Issues in Information SystemsNEURAL NETWORK MODEL VS. SARIMA MODEL IN FORECASTING KOREAN STOCK PRICE INDEX (KOSPI)
38 Citations2007Kyungjoo Lee, Sehwan Yoo +1 more
This study investigates whether the back-propagation neural network (BPNN)model outperforms the seasonal autoregressive integrated moving average (SARIMA) model in forecasting the Korea Composite Stock Price Index (KOSPI) and its return.
Stock Price Prediction: Comparison of Arima and Artificial Neural Network Methods - An Indonesia Stock's Case
32 Citations2010Yohanes Budiman Wijaya, S. Kom +1 more
The results of the study showed that forecasting using Artificial Neural Network method has higher accuracy value than the results with ARIMA method.
International Business ResearchOptimal Combination of Trading Rules Using Neural Networks
26 Citations2009Subrata Kumar Mitra
An experiment is carried out to combine signals generated from of moving averages of different window size using an artificial Neural network and it is observed that the risk adjusted performance measure of the artificial neural network based trading model is better than that of simple ‘Buy and Hold’ strategy.
Comparative results of heuristics for portfolio selection problem
2 Citations2012Aderemi O. Adewumi, Annaliza Moodley
Six heuristic and metaheuristic algorithms are proposed to address constrained PS and indicate that the heuristics suggested can successfully solve the PSP and compete with previously proposed heuristic techniques.