Mykolo Romerio universiteto mokslo valdymo sistema (CRIS)





Mokslininko profilio nuoroda: https://cris.mruni.eu/cris/handle/007/23205
Rodoma1 - 3 iš 3
  • research article[2021][S1][S001,S004][14]
    Gasparėnienė, Ligita
    ;
    ; ;
    Vėbraitė, Vigita
    Inžinerinė ekonomika = Engineering economics. Kaunas : Kaunas University of Technology, 2021, vol. 32, no. 4., p. 362-375

    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.

      19Scopus© citavimai 13
  • conference paper[2019][P1c][S004][16];
    Whither our economies - 2019 : International scientific conference : conference proceedings. Vilnius : Mykolas Romeris University, 2019, [vol.] 6., p. 30-45

    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.

      10
  • conference paper[2016][T1c][S004,S003][3];
    Whither our economies - 2016 : 5th international scientific conference, October 20-21, 2016 : conference proceedings [Elektroninis išteklius] / Mykolas Romeris University. Faculty of Economics and Finance Management. Vilnius : Mykolas Romeris University, 2016, T. 5., p. 205-207

    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.

      3