期刊名称：International Journal of Advances in Engineering and Management
电子版ISSN：2395-5252
出版年度：2021
卷号：3
期号：6
页码：450-459
DOI：10.35629/5252-0306341346
语种：English
出版社：IJAEM JOURNAL
摘要：It is the desire for the Share market investors in a country is to have access to reliable forecast of gold prices. This is achievable if an appropriate model with high predictive accuracy is used. The main object of this paper is to compare the Time series models with Machine learning algorithm.The ARIMA model is developed to forecast Indian Gold prices using daily data for the period 2016 to 2020 obtained from World Gold Council.We fitted the ARIMA (2,1,2) model to our data and we picked this model which exhibited the least AIC values. Random forest and XGB algorithmsare also used by taking two lagged variables as an independent variables of dependent variable.The forecasting performance of the models evaluated using mean absolute error, mean absolute percentage error and root mean squared errors. XGB model outperforms than that of the other two models for forecasting the Gold prices in India.
关键词：Gold Prices;Box-Jenkins Methodology;ARIMA.lag variables;Random forest model;XGB model
