Abstract

Awareness about the price of precious metals and the correct prediction on the process of taking decision can bring facilities, and purchasing them in the global market and recognizing the specific time of dealing can cause investment. In this article comparison of the performance of Artificial Neural Networks and Fuzzy Inference Systems in predicting the price of the precious metals (Case Study: Gold, Silver, Platinum and Palladium).has been pointed. The information about each of these metals (Gold, Silver, Platinum and Palladium) is monthly considered from 1998 until 2018 including 360 data. Thus, by examining different influential variables, National Product Parameters, Time, getting higher the value of USD dollar against the Canadian dollar, global production and global reserves of precious metals are chosen as influential variables. In this research, implementation of (ANFIS) is made for the prediction model by using Artificial and Fuzzy Neural Model. Evaluation of models by using coefficient values, the average set of squares and the square root of the average set of the squares in order of the values for Gold 0.9964 , 0.000268 & 0.01637 for silver 0.987, 0.000092 & 0.0096, for platinum 0.9976, 0.000209 & 0.01448 and for palladium 0.99, 0.0001 & 0.01 have been achieved. As a result, while the best predictive model for the price of gold and platinum is Artificial Neural Networks, the model of ANFIS is suggested for the silver and palladium.

References

[1] Alameer, Z., and Elaziz M. A, 2019. Forecasting gold price fluctuations using improved multilayer Perceptron neural network and whale optimization algorithm. Resources policy.

[2] Yang, J., Li, X., Liu, Q., 2017. China's copper demand forecasting based on system dynamics model: 2016-2030. Journal of Residuals Science & Technology, Volume 14, No 3.651-

[3] Anish, C.M,.and Majhi, Babita. 2016. Hybrid nonlinear adaptive scheme for stock market prediction Using feedback FLANN and factor analysis. Jouranal of the Korean Statistical Society.

[4] Adebiyi, A.A., and Ayo, C, k. 2011.Fuzzy Neural Model with hybrid market indicators for stock Forecasting. Int. J. Electronic Finance.

[5] Atsalakis, George S, and Balavanis, Kimon P. 2009. Forecasting stock market short-term trends Using a neuro- fuzzy based methododlgy. Expert Systems with Applecations.

[6] Amjadi N., Keynia F., and Zareipour H., 2011.Wind Power Prediction by a New Forecast Engine Composed of Modified Hybrid Neural Network and Enhanced Particle Swarm Optimization. IEEE Trans. Sustainable Energy.

[7] Antonino, Parisi. And franco parisi.,david diaz.2010.Forecasting gold price changes:Rolling  and Recursive neural network models.Journal of multinational financial management.

[8] Balcilar, M., Dalkilic, A., and Wongwises, S., 2011. Artificial neural network techniques for the Determination of condensation heat transfer characteristics during downward annular flow of R134a Inside a vertical smooth tube. International Communications in Heat and Mass Transfer.

[9] Boyacioglu, Melek Acar, And Avci, Derya. 2010. An Adaptive Network – Based Fuzzy Inference System (ANFIS) for the prediction of stock market return: the case of the Istanbul Stock Exchange. Management School and Economics.

[10] Baltagi, B. H., Egger, P. and Pfaffermayr, M. 2006. A generalized spatial panel data model with Random effects. Working paper, Syracuse University, Department of Economics and Center for Policy Research.

[11] Cortez, C. A. T., Saydam, S., Coulton, J., and Sammut, C. 2017. International Journal of Mining Science and Technology Alternative techniques for forecasting mineral Commodity prices. International Journal of Mining Science and Technology.

[12] Chen, Hsin-Hung., Chen, Mingchin., and Chiu, Chun-Cheng. 2014. The Integration of Artificial Neural Networks and Text Mining to Forecast Gold Futures Prices.  Communications in Statistics—Simulation and Computation.

[13] Dehghani,H., and Ataee-pour,M.2011.Determination of the effect of operating cost uncertainty on miningproject evaluation. Resources Policy

[14] Dehghani,H. , Ataee-pour,M., and Esfahanipour,A. 2014. Evaluation of the mining projects under Economic uncertainties using multidimensional binomial tree. Resources Policy.

[15] Desai, V. S., and Bharati, R. 2008. A comparison of linear regression and neural network methods For predicting excess returns on large stocks.Annals of Operations Research.

[16] Elyasiani, E., Mansur, I., and Odusami, B. 2011. Oil price shocks and industry stock returns.Energy Economics