Estimating Malaysia gold prices via nonlinear prediction model / Syazwani Zainal Abidin, Nur Fatihah Haron and Siti Fudzla A'ini Mokhtar

This paper focuses on the development of the price of gold. Gold has been considered a safe return investment because of its characteristic to hedge against inflation. Gold prices prediction is an essential tool especially to the investors who have problems for making decisions whether they are supposed to buy or sell the gold because they do not have a specific method to determine exactly when the gold prices will increase or decrease at the current situation. Therefore, the purpose of this study is to search and find the possible chaotic behavior of gold prices by Nonlinear Prediction (NLP) method using theory of chaos involving daily gold prices data in Malaysia from January 2016 to June 2016. Nonlinear prediction method involves the reconstruction of phase space and local linear approximation approach. The phase space reconstruction involves the reconstruction of one-dimensional data into a multidimensional phase space to reveal the dynamics of the system. Revenue of phase space reconstruction was used to predict the daily gold prices. A comparison of prediction performance based on Root Mean Square Error (RMSE) was employed to compare prediction performance for NLP and Linear Least Square Method (LLSM). Prediction performance comparisons shows that the prediction results using NLP method are better. Thus, NLP method is recommended by using many variables to construct the dimensions. Hence, this paper provides a summary of how price of gold can benefits to the investors to provide a better view of the gold prices movement and gold investment.