Search results

1

Porównanie wybranych metod statystycznych i metod sztucznej inteligencji do przewidywania zdarzeń w oprogramowaniu zabezpieczającym systemy przechowywania dokumentów cyfrowych, w tym systemy klasy Enterprise Content Management

100%

Sapała K., Piołun-Noyszewski M., Weiss M.

Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu

|

2017

|

issue 469

159-166

PL

W ostatnich latach nastąpił wzrost zainteresowania wykorzystywaniem metod statystycznych do analizy zdarzeń z zakresu bezpieczeństwa teleinformatycznego. Coraz częściej moduły analityczne implementuje się w systemach chroniących przedsiębiorstwa przed zagrożeniami. Bardzo duże znaczenie ma w tej dziedzinie automatyzm i wykonywanie analiz bez nadzoru człowieka. W pracy opisane zostały efekty zastosowania działających automatycznie modułów eksperckich do przewidywania wartości szeregów czasowych, w sytuacji gdy nie były znane ich własności. Bez zastosowania właściwych metod przekształcenia szeregu i odpowiedniej parametryzacji tworzone modele mogą w wielu sytuacjach działać niepoprawnie. Natomiast w przypadku mających charakter cykliczny szeregów uzyskiwane prognozy mogą stanowić wartościową informację o potencjalnym zagrożeniu dla bezpieczeństwa przedsiębiorstwa.

2

Application of Box-Jenkins method and Artificial Neural Network procedure for time series forecasting of prices

100%

Singh A., Mishra G. C.

Statistics in Transition new series

|

2015

|

vol. 16

|

issue 1

83–96

EN

Forecasting of prices of commodities, especially those of agricultural commodities, is very difficult because they are not only governed by demand and supply but also by so many other factors which are beyond control, such as weather vagaries, storage capacity, transportation, etc. In this paper time series models namely ARIMA (Autoregressive Integrated Moving Average) methodology given by Box and Jenkins has been used for forecasting prices of Groundnut oil in Mumbai. This approach has been compared with ANN (Artificial Neural Network) methodology. The results showed that ANN performed better than the ARIMA models in forecasting the prices.

3

Forecasting Future Salaries in the Czech Republic Using Stochastic Modelling

75%

Šimpach O., Langhamrová J.

Business Systems Research Journal

|

2013

|

vol. 4

|

issue 2

4-125

EN

Background: In spite of the course of the economic crisis of 2008, there have not been changes dramatic to the extent that they would strongly alter the behaviour of the trend in the Average Gross Monthly Wages and the Monthly Wage Medians in the Czech Republic. In order to support public and monetary planning, reliable forecasts of future salaries are indispensable. Objectives: The aim is to provide an outline of the behaviour of the average gross wages and the gross wage medians of the Czech business sphere up to the end of 2018 using an optimised random walk model and an optimised ARIMA Model with a constant. Methods: Consumer price indices were used in the confrontation of the behaviour of the Average Gross Monthly Wages and the Monthly Wage Medians with the behaviour of inflation in the Czech Republic. The Box-Jenkins methodology is used for the time series modelling. Results: The Czech Average Gross Monthly Wages and the Monthly Wage Medians in the business sector will continue to grow more rapidly than the Czech inflation growth, expressed by consumer price indices. Conclusions: It is possible to expect that the rising trend of the Average Gross Monthly Wages and the Gross Wage Medians will be more rapid than the growth of inflation.

4

The modeling of earnings per share of Polish companies for the post-financial crisis period using random walk and ARIMA models

75%

Kuryłek W.

Journal of Banking and Financial Economics

|

2023

|

issue 1(19)

26-43

EN

The proper forecasting of listed companies’ earnings is crucial for their appropriate pricing. This paper compares forecast errors of different univariate time-series models applied for the earnings per share (EPS) data for Polish companies from the period between the last financial crisis of 2008–2009 and the pandemic shock of 2020. The best model is the seasonal random walk (SRW) model across all quarters, which describes quite well the behavior of the Polish market compared to other analyzed models. Contrary to the findings regarding the US market, this time-series behavior is well described by the naive seasonal random walk model, whereas in the US the most adequate models are of a more sophisticated ARIMA type. Therefore, the paper demonstrates that conclusions drawn for the US might not hold for emerging economies because of the much simpler behavior of these markets that results in the absence of autoregressive and moving average parts.

5

Zastosowanie modelu ARIMA do krótkookresowego prognozowania wielkości ruchu pasażerskiego na przykładzie Międzynarodowego Portu Lotniczego w Krakowie-Balicach

75%

Rudnicki M.

Zeszyty Naukowe Uniwersytetu Ekonomicznego w Krakowie

|

2012

|

issue 885

175-191

EN

The article sought to answer the question of whether the downward spiral of tourist traffic will continue at John Paul II International Airport Kraków-Balice in 2010. A revision of earlier forecasts drawn up at the end of 2009, the study also seeks to determine whether the number of guests served at the airport could return to the record 3 million passengers served in 2007. To this end, I introduce an analysis of the volume of tourist traffic for the years 2003–2009, based on passenger traffic statistics collected by the International Airport. The ARIMA model was used to produce forecasts for 2010. This study is extremely important because, as analysis shows, there is a direct correlation between the volume of passenger traffic at Kraków’s airport and the number of tourists in the city. Therefore, the results of this study may help identify the estimated volume of tourist traffic in Kraków in 2010, which is crucial to the tourism economy of the city and its inhabitants.

6

Modelling and Prognosis of the Export of the Republic of Serbia by Using Seasonal Holt-Winters and Arima Method

75%

Mladenović J., Lepojević V., Janković-Milić V.

Economic Themes

|

2016

|

vol. 54

|

issue 2

233-260

EN

Low labour costs as one of the key sources of export stimulation, the competitive advantage of domestic agricultural production and bilateral agreements with partner countries - all promote export as a potentially significant factor of encouragement of economic development of the Republic of Serbia.Taking into account this fact, on the one hand, and balance of payments problems that Serbia has been facing over the years, on the other hand, the subject of this paper is an analysis of trends in the Republic of Serbia export and explanation of variations in the export trends during the period from 2004 to 2014. The aim of the paper is to explore export trends forecast from January to December 2015.The analysis uses Holt-Winters and ARIMA methods for analyszing time series.The paper provides insight into the export trend forecasts for the period of 12 months, and thus confirms the possibility of practical usage of the time series analysis methods in forecasting macroeconomic variables such as export. The used methods identify increase of export during the summer and its decrease after October 2015. The paper establishes the existence of a high degree of congruence between forecasts obtained by using two methods, which confirm a high quality of the elaborated methods in the analysis of exports.

7

Ocena efektów dywersyfikacji portfela produktowego w zakresie ryzyka sprzedaży całkowitej i trafności jej prognoz

75%

Brzęczek T.

Econometrics. Ekonometria. Advances in Applied Data Analytics

|

2017

|

issue 1 (55)

112-124

PL

Celem prac badawczych opisanych w artykule była ocena dywersyfikacji portfela produktowego w świetle pojęć i metod teorii prognozowania, przede wszystkim ocena dywersyfikacji na podstawie trafności prognozy sprzedaży całkowitej. Dlatego porównano trafność prognoz sprzedaży pojedynczych grup produktów i sprzedaży całkowitej w wybranym przedsiębiorstwie handlowym z branży rolniczo-technicznej. Wyniki są zgodne ze znaną z teorii prawidłowością, iż dywersyfikacja produktowa służy zmniejszaniu ryzyka w prowadzonej działalności gospodarczej. Podwyższona trafność prognoz potwierdziła hipotezę o właściwej dywersyfikacji produktowej w badanym przedsiębiorstwie. Dobór metod i estymację modeli poprzedzono badaniami własności szeregów czasowych sprzedaży. Testy dały ogólne wskazówki co do typu modelu i zmiennych objaśniających. Do analizy każdego szeregu zastosowano alternatywne typy modeli: regresji, ARIMA i wygładzania wykładniczego Wintersa, z których wybrano jeden o najbardziej trafnych prognozach.

8

Využití administrativních dat v oblasti vynucování práva pro analýzy aplikující statistické modely využívající informace o čase: příklad drogových politik

63%

Petruželka B.

Česká kriminologie (Czech Criminology)

|

2021

|

vol. 6

|

issue 1-2

1-21

EN

Criminologists try to understand the nature of various changes, such as what leads to changes in crime. One of the shortcomings of criminology, especially in a Czech context, is the underdeveloped field of statistical modeling based on time-specific information. The aim of this article is to discuss the possibilities and limits of administrative data in the field of law enforcement while applying statistical models using time-specific information. Selected methods based on the use of data containing time-specific information, through the application of time series analysis, are presented: ARIMA models and structural change models. Furthermore, examples of such analyses are provided and a theoretical framework which facilitates the use of time series models is outlined. In addition, the availability of the data needed for such analyses is assessed.

Refine search results

1 Business Systems Research Journal

1 Econometrics. Ekonometria. Advances in Applied Data Analytics

1 Economic Themes

1 Journal of Banking and Financial Economics

1 Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu

1 Statistics in Transition new series

1 Zeszyty Naukowe Uniwersytetu Ekonomicznego w Krakowie

1 Česká kriminologie (Czech Criminology)

1 Brzęczek T.

1 Janković-Milić V.

1 Kuryłek W.

1 Langhamrová J.

1 Lepojević V.

1 Mishra G. C.

1 Mladenović J.

1 Petruželka B.

1 Piołun-Noyszewski M.

1 Rudnicki M.

1 Sapała K.

1 Singh A.

1 Weiss M.

1 Šimpach O.

1 2023

1 2021

2 2017

1 2016

1 2015

1 2013

1 2012