Predicting the Brazilian stock market through neural networks and adaptive exponential smoothing methods

Faria, Elisângela L.; Albuquerque, Marcelo P. de; González, Jeanette; Cavalcante, José Thadeu Pinto; Albuquerque, Márcio P. de

doi:10.1016/j.eswa.2009.04.032

Cited by 113 publications

(55 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Using six evaluation criteria (MAE, RMSE, MAPE, CORR, DA & SIGN), they found that NN has superior in-sample forecast than linear autoregressive and random walk models. Studies done by [76][77][78][79][80][81][82][83][84][85][86][87][88][89][90][91], [49], [92][93][94][95][96][97][98][99][100][101][102][103][104] are also in the same category, which concluded NNs have superior performance comparing to other traditional methods. Table 5 presents the brief results of these comparisons.…”

Section: Financial Prediction and Planningmentioning

confidence: 67%

A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems

Bahrammirzaee

2010

Neural Comput & Applic

442

192

View full text Add to dashboard Cite

Nowadays, many current real financial applications have nonlinear and uncertain behaviors which change across the time. Therefore, the need to solve highly nonlinear, time variant problems has been growing rapidly. These problems along with other problems of traditional models caused growing interest in artificial intelligent techniques. In this paper, comparative research review of three famous artificial intelligence techniques, i.e., artificial neural networks, expert systems and hybrid intelligence systems, in financial market has been done. A financial market also has been categorized on three domains: credit evaluation, portfolio management and financial prediction and planning. For each technique, most famous and especially recent researches have been discussed in comparative aspect. Results show that accuracy of these artificial intelligent methods is superior to that of traditional statistical methods in dealing with financial problems, especially regarding nonlinear patterns. However, this outperformance is not absolute.

show abstract

Section: Financial Prediction and Planningmentioning

confidence: 67%

A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems

Bahrammirzaee

2010

Neural Comput & Applic

442

192

View full text Add to dashboard Cite

show abstract

“…The second method is guided by forecasts on the direction/sign of the changes in price levels. This latter approach is defended by some authors (e.g., see Wu & Zhang, 1997;Aggarwal & Demaskey, 1997;Tsaih, Hsu & Lai, 1998;Leung, Daouk & Chen, 2000;Chen, Leung & Daouk, 2003;Kim, Min & Han, 2006;Faria et al, 2009;Lu, 2010;Na & Sohn, 2011), who claim that trading driven by a certain forecast with a small forecast error may not be as profitable as trading based on an accurate prediction of the direction/sign of the movement.…”

Section: Introductionmentioning

confidence: 99%

S&P 500 Index Direction Forecasting from 1976 to 2010: A Fuzzy System Approach

Souto-Maior¹,

Borba²,

Costa³

2011

IJDAR

View full text Add to dashboard Cite

Abstract. Investors are not always completely rational and they do not always work only with numbers. Sometimes, they use linguistic concepts to make their decisions. Fuzzy logic is helpful in handling such situations. This article differs from other studies in this area by applying fuzzy logic for forecasting the direction/sign of stock market indexes. The article also presents a model for forecasting the direction/sign of stock market indexes using a fuzzy system, and this model is applied in the prediction of the S&P 500 Index. The rules of the model were established between 1970 and 2009, and the test period was from 1976 to 2010. Despite the fact that the estimated model produced a linguistic output, it was possible to delineate a statistically significant investment strategy, which outperformed a buy-and-hold one. In addition, the success rate calculated was also statistically significant. Another difference from other studies is that the proposed model does not return an exact output, but a probabilistic one of linguistic variables. The proposed model, with its probabilistic output, can be used as a support for investment decisions. In other words, the linguistic output does not force the investor to blindly follow the proposed strategy.

show abstract

“…It does not matter whether the forecasts are accurate or not in terms of normalized mean squared error (NMSE) or gradient (Yao & Tan, 2000). For example (O"Connor & Madden, 2006) and (De Faria, Albuquerque, Gonzalez, Cavalcante, & Albuquerque, 2009) found that there is a disparity between RMSE and profitability of the ANN model. Which means that obtaining low RMSE does not provide high returns, in other words the relationship is not linear between two.…”

Section: Introductionmentioning

confidence: 99%

Stock Market Prediction Performance of Neural Networks: A Literature Review

İcan¹,

Çeli̇k²

2017

IJEF

View full text Add to dashboard Cite

In this paper, previous studies featuring an artificial neural networks based prediction model have been reviewed. The main purpose of this review is to examine studies which use directional prediction accuracy (also known as hit ratio) or profitability of the model as a benchmark since other forecast error measures -namely mean absolute deviation (MAD), root mean squared error (RMSE), mean absolute error (MAE) and mean squared error (MSE) -have been criticized for the argument that they are not able to actually show how useful the prediction model is, in terms of financial gains (i.e. for practical usage). In order to meet the publication selection criteria mentioned above, a large number of publications have been examined and 25 of papers satisfying the criteria are selected for comparison. Classification of the eligible papers are summarized in a table format for future studies.

show abstract

Predicting the Brazilian stock market through neural networks and adaptive exponential smoothing methods

Cited by 113 publications

References 27 publications

A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems

A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems

S&P 500 Index Direction Forecasting from 1976 to 2010: A Fuzzy System Approach

Stock Market Prediction Performance of Neural Networks: A Literature Review

Contact Info

Product

Resources

About