Prediction of Gold Price Movement Considering the Number of Infected With the Covid 19




Abstract:
The beginning of the health and economic crisis caused by the appearance of the new Covid-19 virus showed us that, in the perception of investors, gold is still highly valued as a guardian of value. This paper aims to test several models and select the best one for predicting the price of gold on the world market for the next day, in five and ten days, taking into account the number of cases and deaths from the Covid-19 virus. We believe that predictions with Covid-19 parameters give more accurate results than predictions that take only historical gold prices as information. These predictions can help decision-makers whether, at what point, and in what amount, it is best to invest in gold and gold-related financial instruments, relative to the projected price of gold from the model. The paper tests models called Decision tree, K-nearest neighbours, Linear regression model, and Support vector machine based on the information on gold prices and the number of cases and deaths from the Covid-19 virus. It will be seen in the paper that even models with only information on the price of gold give quite reliable predictions, but in unstable times like this, models that take into account the instability factor give more accurate predictions. The research is aiming to determine the optimal amount of information on which the models will "learn" to give the most accurate possible result. This work’s data processing and models are done in the Python programming language.

CITATION:

IEEE format

J. Stokanovic Sevic, A. Jovancai Stakic, “Prediction of Gold Price Movement Considering the Number of Infected With the Covid 19,” in Sinteza 2022 - International Scientific Conference on Information Technology and Data Related Research, Belgrade, Singidunum University, Serbia, 2022, pp. 58-64. doi:10.15308/Sinteza-2022-58-64

APA format

Stokanovic Sevic, J., Jovancai Stakic, A. (2022). Prediction of Gold Price Movement Considering the Number of Infected With the Covid 19. Paper presented at Sinteza 2022 - International Scientific Conference on Information Technology and Data Related Research. doi:10.15308/Sinteza-2022-58-64

BibTeX format
Download

RefWorks Tagged format
Download