Sosidko, Aleksejus

In order to forecast stock prices based on economic indicators, many studies have been conducted using well-known statistical methods. Meanwhile, since ~2010 as the power of computers improved, new methods of machine learning began to be used. It would be interesting to know how those algorithms using a variety of mathematical and statistical methods, are able to predict the stock market. The purpose of this article is to model the monthly price of the S&P 500 index based on U.S. economic indicators using statistical, machine learning, deep learning approaches and finally compare metrics of those models. After the selection of indicators according to the data visualization, multicollinearity tests, statistical significance tests, 3 out of 27 indicators remained. The main finding of the research is that the authors improved the baseline statistical linear regression model by 19 percent using a ML Random Forest algorithm. In this way, model achieved accuracy 97.68 % of prediction S&P 500 index.

There are a big number of researches which analyzing stock price returns. Some of them is based on fundamental analysis theory. Meanwhile other studies are based on efficient market hypotheses and financial behavior theories. However, there is not enough researches combining the characteristics of these theories into one. Such kind of researches in the scientific literature is usually referred to macroeconomic news, announcements, surprises, expectations studies. These studies examine not only the actual but also the predictive values of macroeconomic indicators announcements, normalizing them and thus creating absolutely a new surprise indicator. Purpose of this paper is modeling EURO STOXX 50 index price returns based on Industrial production surprise indicator. Empirical part shows that the best models for explaining EURO STOXX 50 index price returns was obtained at the 40 and 42 in different surprise indicator scenario. The coefficient of determination was obtained respectively 24.70% and 21,80%. Meanwhile applying machine learning method of artificial intelligence, a much more accurate models were obtained. The coefficient of determination respectively was 33,22% and 26,60%.

In this paper are evaluating the impact of unemployment rate announcement on the Euro Stoxx 50 index returns on the basis of a semi-strong efficient market hypothesis. Analyzing and summarizing previous researches of semi-strong market efficiency find, that there are various studies analyzing the returns of stock market depending on corporate financial statements announcement, but there are only a few that analyze the returns of stock market of macroeconomic announcement, and especially announcement about the unemployment rate. In this study the semi-strong effective market hypothesis is determined in a very short time interval of 5 minutes from 11:00 to 11:04, therefore the MKAR, RAR methods to determine the Euro Stoxx 50 index returns are used. The originality of the study is that the values of the models were calculated on the basis of high frequency data, not daily data. In this empirical research non-zero values of MKAR, RAR models were obtained, which indicate that in the analyzed 4/4/2018 - 1/4/2019 period the Euro Stoxx 50 index is not a semi-strong effective based on of unemployment rate announcement. It was also found that Euro Stoxx 50 index returns on the fifth minute (11:04) after the unemployment rate announcement realize (11:00) can earn more, or less than the comparable stock market indexes returns.

This article evaluates fluctuations in the Standard & Poor’s 500 sectoral index prices, taking into account the impact of fundamental macroeconomic stock price determinants assessed by individual expectation categories. Models for stock price prognostication have also been developed and verified. In this research, fluctuations in the Standard & Poor’s 500 sectoral index prices are evaluated, taking into account each fundamental macroeconomic determinant and a separate expectation category. This research has enabled the identification of indices with high price fluctuations. Statistically reliable prognostication models have been empirically verified, and the most reliable prognostication models for indicating rise or declines in index prices have been identified.

The article covers evaluation of fluctuations of Standard & Poors 500 sectoral index prices considering the impact of fundamental macroeconomic stock price determinants, assessed by individual expectation categories. Also, the models for stock price prognostication have been developed and verified. In the research, fluctuations of Standard & Poors 500 sectoral index prices are evaluated considering each fundamental macroeconomic determinant and a separate expectation category. The res earch has enabled to identify the indices with high price fluctuations. Statistically reliable prognostication models have been empirically verified, and the most reliable prognostication models, which could indicate index price rise or decline, have been revealed.