English Predvidjanje cene zlata uzimajuci u obzir broj zarazenih virusom Covid 19
Sažetak
Početak zdravstvene i ekonomske krize izazvane pojavom novog virusa Covid-19 pokazao nam je da je u percepciji investitora zlato i dalje visoko cenjeno kao čuvar vrednosti.
Ovaj rad ima za cilj da testira nekoliko modela i odabere najbolji za predviđanje cene zlata na svetskom tržištu za naredni dan, za pet i deset dana, uzimajući u obzir broj obolelih i umrlih od virusa Covid-19.
Verujemo da predviđanja sa parametrima Covid-19 daju tačnije rezultate od predviđanja koja kao informaciju uzimaju samo istorijske cene zlata.
Ova predviđanja mogu pomoći donosiocima odluka da li je, u kom trenutku i u kom iznosu, najbolje investirati u zlato i finansijske instrumente vezane za zlato, u odnosu na projektovanu cenu zlata iz modela.
U radu se testiraju modeli pod nazivom Decision tree, K-nearst neighbours, model linearne regresije i Support vector machine na osnovu informacija o cenama zlata i broju slučajeva i smrti od virusa Covid-19.
U radu će se videti da čak i modeli sa samo podacima o ceni zlata daju prilično pouzdana predviđanja, ali u ovakvim nestabilnim vremenima, modeli koji uzimaju u obzir faktor nestabilnosti daju tačnija predviđanja.
Istraživanje ima za cilj da odredi optimalnu količinu informacija na kojoj će modeli „naučiti“ da daju što tačniji mogući rezultat.
Obrada podataka i modeli ovog rada su urađeni u programskom jeziku Python.
Reference
[1] | I. Yousef, E. Shehadeh “The impact of COVID-19 on Gold Price Volatiity,” International Journal of Economics and Business Administration, vol. VIII, no. 4, pp. 353-364, 2020. |
[2] | S.Shafiee, E. Topal, “An Overview of Global Gold Market and Gold Price Forecasting,” Resources Policy, no. 35, p. 178–189, 2010. |
[3] | G. Aye, R. Gupta, S. Hammoudeh, W. Joong Kim, “Forecasting the Price of Gold Using Dynamic Model Averaging,” International Review of Financial Analysis, vol. 41, p. 257–66, 2015. |
[4] | A. Azzuti, Forcasting Gold Price A Comparative Study, 2016. |
[5] | X. Yang., “The prediction of gold price using ARIMA model,” in 2nd International Conference on Social Science, Public Health and Education (SSPHE 2018), Atlantis Press, 2019. |
[6] | J. Brownlee, “Machine Learning Mastery,” 2020. [Online]. Available: https://machinelearningmastery.com/arima-for-time-series-forecasting-with-python/. [Accessed 12 6 2020]. |
[7] | M. Riazuddin, “Towards Data Science,” [Online]. Available: https://towardsdatascience.com/machine-learning-to-predict-gold-price-returns-4bdb0506b132. [Accessed 20 4 2020]. |
[8] | H. Mombeini, A. Chamzini, “Modeling Gold Price via Artificial Neural Network,” Journal of Economics, Business and Management., vol. 3, pp. 699-703., 2015. |
[9] | U. Hong, N. Majid, “Comparison of ARIMA model and artifical neural network in forcasting gold price,” Journal of Quality Measurement and Analysis, vol. 2, no. 17, pp. 31-39, 2021. |
[10] | P. Megan, “Stanford,” 2013. [Online]. Available: http://cs229.stanford.edu/proj2013/Potoski-PredictingGoldPrices.pdf. [Accessed 12 1 2022]. |
[11] | J. Test, M. Broker, Machine learning for algorithm trading: Master as a PRO applied artifical inteligence and Python for predict systematic strategies for option and stocks., Independently published, 2020. |
[12] | S. Perry, “Predicting Gold and Silver Price Direction Using Tree-Based Classifiers,” Journal of Risk and Financial Manag., vol. 5, no. 14, p. 198, 2021. |
[13] | D. Navin, “Big Data Analytics for Gold Price Forecasting Based on Decision Tree Algorithm and Support Vector,” International Journal of Science and Research, vol. 4, no. 3, pp. 2026-2030, 2015. |
[14] | I. Shah, R. Panchekar, “Quantisti,” [Online]. Available: https://blog.quantinsti.com/gold-price-prediction-using-machine-learning-python/. [Accessed 8 7 2020]. |
[15] | S. A. Dudani, “The Distance-Weighted k-Nearest-Neighbor Rule,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 6, no. 4, pp. 325 - 327, 1976. |
[16] | G. Van den Burg, P. Groenen, “GenSVM: A Generalized Multiclass Support Vector Machine,” Journal of Machine Learning Research, vol. 17, no. 224, pp. 1-42, 2016. |