Wyniki wyszukiwania - BazTech

1

Analysis of the Effect of News Sentiment on Stock Market Prices through Event Embedding

Sridhar Sashank, Sanagavarapu Sowmya

Annals of Computer Science and Information Systems

|

2021

|

Vol. 25

147--150

EN

Stock market price prediction models have remained a prominent challenge for the investors owing to their volatile nature. The impact of macroeconomic events such as news headlines is studied here using a standard dataset with closing stock price rates for a chosen period by performing sentiment analysis using a Random Forest classifier. A Bi-LSTM time-series forecasting model is constructed to predict the stock prices by using the polarity of the news headlines. It is observed that Random Forest Classifiers predict the polarity of news articles with an accuracy of 84.92%.

2

Predicting automotive sales using pre-purchase online search data

Wachter Philipp, Widmer Tobias, Klein Achim

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

569--577

EN

Sales forecasting is an essential element for implementing sustainable business strategies in the automotive industry. Accurate sales forecasts enhance the competitive edge of car manufacturers in the effort to optimize their production planning processes. We propose a forecasting technique that combines keyword-specific customer online search data with economic variables to predict monthly car sales. To isolate online search data related to pre-purchase information search, we follow a backward induction approach and identify those keywords that are frequently applied by search engine users. In a set of experiments using real-world sales data and Google Trends, we find that our keyword-specific forecasting technique reduces the out-of-sample error by 5\% as compared to existing techniques without systematic keyword selection. We also find that our regression models outperform the benchmark model by an out-of-sample prediction accuracy of up to 27%.

3

Pomierzone i prognozowane krzywizny terenu górniczego na przykładzie obserwacji geodezyjnych z KWK "Budryk"

Mielimąka R.

Górnictwo i Geologia

|

2006

|

T. 1, z. 4

81-92

PL

W artykule dokonano oceny dokładności prognozowania krzywizn programami komputerowymi, z wykorzystaniem wzorów teorii Budryka-Knothego i rozszerzeń tej teorii, opracowanych przez J. Białka. Podstawę oceny stanowiły krzywizny uzyskane z pomiarów wysokościowych, prowadzonych cyklicznie na linii obserwacyjnej 1 KWK "Budryk", na której zarejestrowano ich wartości po kolejnej eksploatacji czterech ścian w pokładzie 338/2. Wykazano, że rzeczywisty przebieg końcowych krzywizn dość istotnie różni się od ich przebiegu teoretycznego, a dokładność opisu tych krzywizn zmniejsza się wraz z postępującą, nierównomierną dezintegracją górotworu, spowodowaną eksploatacją kolejnych ścian.

EN

The paper presents the assessment of prediction accuracy of curvatures carried out with the use of computer programs, with the application of the equations of Budryk-Knothe theory and the extension of this theory elaborated by J. Białek. The prediction assessment was based on curvatures obtained from the altimetric measurements carried out cyclically along measurement line 1 of the "Budryk" coal mine. These measurements have been conducted after another exploitation of 4 side walls in coal seam number 338/2. The study shows that the real course of final curvatures quite significantly differs from the theoretical course. The accuracy of the prediction decreases with advance of the irregular disintegration of rock strata caused by exploitation of consecutive side walls.

4

Application of modern portfolio theory to the Russian state bond market

Pervozvanskij A., Barinov V., Kozlova O.

Control and Cybernetics

|

1999

|

Vol. 28, no 4

799-810

EN

The behaviour of the Russian state bond market is analyzed. Attention is mainly paid to short-term fluctuations and efficiency of short-term investments. Analysis of return time series has shown that there exists a significant autocorrelation, and that distribution of random fluctuations is non-Gaussian. It predetermines a choice of forecasting schemes. The most efficient ones appear to be non-linear. The efficiency was checked not only by the traditional statistical indices by direct numerical experiments where various types of predictors were used as basic elements of decision rules. The decision algorithms have included the solution to the modified optimal portfolio problem where the forecasts were used as expected returns and the covariance matrix was estimated via forecasting errors.