Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Nov 14;12(11):e0188107.
doi: 10.1371/journal.pone.0188107. eCollection 2017.

Predictability of machine learning techniques to forecast the trends of market index prices: Hypothesis testing for the Korean stock markets

Sujin Pyo  1 , Jaewook Lee  1 , Mincheol Cha  1 , Huisu Jang  1
Affiliations

Predictability of machine learning techniques to forecast the trends of market index prices: Hypothesis testing for the Korean stock markets

Sujin Pyo et al. PLoS One. .

Abstract

The prediction of the trends of stocks and index prices is one of the important issues to market participants. Investors have set trading or fiscal strategies based on the trends, and considerable research in various academic fields has been studied to forecast financial markets. This study predicts the trends of the Korea Composite Stock Price Index 200 (KOSPI 200) prices using nonparametric machine learning models: artificial neural network, support vector machines with polynomial and radial basis function kernels. In addition, this study states controversial issues and tests hypotheses about the issues. Accordingly, our results are inconsistent with those of the precedent research, which are generally considered to have high prediction performance. Moreover, Google Trends proved that they are not effective factors in predicting the KOSPI 200 index prices in our frameworks. Furthermore, the ensemble methods did not improve the accuracy of the prediction.

PubMed Disclaimer

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Artificial neural network.
There are three layers; an input layer, hidden layers, and an output layer. Inputs are inserted into the input layer, and each node provides an output value via an activation function. The outputs of the input layer are used as inputs to the next hidden layer.
Fig 2
Fig 2. Support vector machine.
Given data set of n points (x1, y1), (x2, y2), …, (xn, yn) where yi gives -1 or 1 which indicates the class and xi is a p-dimensional vector, we want to classify the points by finding “maximum-margin hyperplane” which divides the data into two groups with at the highest probability. This means that the distance between the hyperplane and the points which are the closest to the hyperplane in each class should be maximized.
Fig 3
Fig 3. The roll-over strategy.
We fix the window for a month and roll over the window to predict next month test data.
Fig 4
Fig 4. Accuracies of prediction of KOSPI 200.
Fig 5
Fig 5. Accuracies of prediction of with and without Google Trend.
Fig 6
Fig 6. Accuracies of prediction using individual companies and KOSPI 200.
See this image and copyright information in PMC

References

    1. Kohzadi N, Boyd MS, Kermanshahi B, Kaastra I. A comparison of artificial neural network and time series models for forecasting commodity prices. Neurocomputing. 1996;10(2):169–181. doi: 10.1016/0925-2312(95)00020-8 - DOI
    1. Kara Y, Boyacioglu MA, Baykan ÖK. Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange. Expert Syst Appl. 2011;38(5):5311–5319. doi: 10.1016/j.eswa.2010.10.027 - DOI
    1. Yoon Y, Swales G. Predicting stock price performance: A neural network approach. In: System Sciences, 1991. Proc Annu Hawaii Int Conf Syst Sci. vol. 4. IEEE; 1991. p. 156–162.
    1. Guresen E, Kayakutlu G, Daim TU. Using artificial neural network models in stock market index prediction. Expert Syst Appl. 2011;38(8):10389–10397. doi: 10.1016/j.eswa.2011.02.068 - DOI
    1. Zahedi J, Rounaghi MM. Application of artificial neural network models and principal component analysis method in predicting stock prices on Tehran Stock Exchange. Phys A. 2015;438:178–187. doi: 10.1016/j.physa.2015.06.033 - DOI

LinkOut - more resources