Using Artificial Intelligence in Analyzing and Predicting the Development of Stock Prices of a Subject Company

Stock prices are developing very dynamically and nonlinearly. The stock price is affected by a number of factors. Stocks are therefore characterized by asymmetric volatility, non-stationarity, and sensitivity. Given these facts and the unpredictability of a global crisis, it is logical that the process of stock price prediction is a complex task. Traditional methods for price prediction are no longer enough; new applications and techniques, such as artificial neural networks, are coming to the forefront. The aim of this contribution is to analyze and predict the evolution of the stock price of Unipetrol, a.s. on the Prague Stock Exchange using artificial neural networks. Stock price data is available between January 2006 and April 2018. The data file is first analyzed. Subsequently, a total of 10,000 multilayer perceptron networks (MLPs) and a basic radial function network (RBF) are generated. A total of five neuron structures with the best characteristics are preserved. Using statistical interpretation, it is found that in practice, the MLP 1-17-1 network is applicable in one business day prediction.

[1]  Shuaishuai Sun,et al.  A DFS Model for Forecasting Stock Price , 2016 .

[2]  Tsung-Sheng Chang,et al.  A comparative study of artificial neural networks, and decision trees for digital game content stocks price prediction , 2011, Expert Syst. Appl..

[3]  J. Vrbka,et al.  Prediction of stock price developments using the Box-Jenkins method , 2017 .

[4]  Mohammad Mahdi Rounaghi,et al.  Application of artificial neural network models and principal component analysis method in predicting stock prices on Tehran Stock Exchange , 2015 .

[5]  Baikunth Nath,et al.  A fusion model of HMM, ANN and GA for stock market forecasting , 2007, Expert Syst. Appl..

[6]  Xiaowei Liu,et al.  Application on stock price prediction of Elman neural networks based on principal component analysis method , 2014, 2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP).

[7]  Nunnapus Benjamas,et al.  Stock price trend prediction using Artificial Neural Network techniques: Case study: Thailand stock exchange , 2016, 2016 International Computer Science and Engineering Conference (ICSEC).

[8]  Lenka Dvořáková.  CZ GDP Prediction via neural networks and Box-Jenkins Method , 2017 .

[9]  Kotaro Hirasawa,et al.  Multi-branch Neural Networks and Its Application to Stock Price Prediction , 2005, KES.

[10]  Daniel Santín.  On the approximation of production functions: a comparison of artificial neural networks frontiers and efficiency techniques , 2004 .

[11]  T. Koutroumanidis,et al.  Forecasting Bank Stock Market Prices with a Hybrid Method: The Case of Alpha Bank , 2011 .