Mogućnost primene matematičko-statističke metode Arima za predviđanje cene nafte

Ivanova, P Biljana; Barjaktarović, Lidija; Ivanov, Đ Ilija

doi:10.5937/vojdelo1806297i

Cited by 2 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, many companies decide to invest available cash into short term investment alternatives on 31st of December, and withdraw (convert) it into the cash in the first half of January. b) currently collected and prepared data based is set for January (existing research of Ivanova et. al, 2018, confirmed that 80% of confident in stock price predicting is possible in January especially in the first seven days of the months in the case of oil trading on global market) and the researches' aim to test is it applicable at all and if so the data base will be expended to incorporate other months/ periods of the year; 2) Existing research for Serbian capital market confirmed that applied machine learning models: a) LS-SVM and SVM are suitable for short term stock market trend prediction Marković et al, 2014a), and b) neural networks can be useful for stock market trend prediction (Kalinić et al, 2012) especially if it is taken in consideration specific characteristics of emerging markets (Ralević et al, 2013).…”

Section: Methodsmentioning

confidence: 99%

Toward stock price forecasting on newly acquired belex dataset

Barjaktarović,

Todorović

et al. 2023

Proceedings of the 10th International Scientific Conference - FINIZ 2023

View full text Add to dashboard Cite

Currently there is a lot of research with the aim of applying machine learning in stock price prediction as one of the challenging trends in fintech. Fintech helps to other stakeholders to make better/optimal financial decisions which will improve their wealth and satisfaction. In this paper, the first steps in examining the potential application of basic machine learning algorithms for the prediction of stock prices on the Belgrade Stock Exchange (BELEX) are presented. The results showed that future research is needed to increase dataset and improve quality of data in order to adapt modern and more advanced machine learning methods to achieve higher accuracy in forecasting stock prices. The additional value of this research is the database that combines data from the BELEX, indicators of the company's success and economic parameters of Serbia's growth in the period from 2010 to 2022 and is the basis not only for this but also for future research.

show abstract

Section: Methodsmentioning

confidence: 99%

Toward stock price forecasting on newly acquired belex dataset

Barjaktarović,

Todorović

et al. 2023

Proceedings of the 10th International Scientific Conference - FINIZ 2023

View full text Add to dashboard Cite

show abstract

Forecast of water consumption in Serbia: ARIMA modeling

Gazdić,

Nikolić

2023

Održivi razvoj

View full text Add to dashboard Cite

Water is a symbol of life. Along with air and food, water is a basic existential need. These facts begin to act more strongly on people's opinion and behavior only when he faced with water supply problems. The question is, how to produce more food in these times of growing need for it, while water resources are limited. The Republic of Serbia has a very significant water capacity. Estimation shows that renewable freshwater resources in Serbia are round 55877.93 million of m 3 /per year (Eurostat, 2020). However, water consumption in Serbia is constantly growing, while population is slightly decreasing, which arise the need for time series analysis of water consumption as a tool for future forecast of water consumption.

show abstract

Mogućnost primene matematičko-statističke metode Arima za predviđanje cene nafte

Cited by 2 publications

References 11 publications

Toward stock price forecasting on newly acquired belex dataset

Toward stock price forecasting on newly acquired belex dataset

Forecast of water consumption in Serbia: ARIMA modeling

Contact Info

Product

Resources

About