A Multivariate Approach to Time Series Forecasting of Copper Prices with the Help of Multiple Imputation by Chained Equations and Multivariate Adaptive Regression Splines

This research presents a novel methodology for the forecasting of copper prices using as input information the values of this non-ferrous material and the prices of other raw materials. The proposed methodology is based on the use of multiple imputation with chained equations (MICE) in order to forecast the values of the missing data and then to train multivariate adaptive regression splines models capable of predicting the price of copper in advance. The performance of the method was tested with the help of a database of the monthly prices of 72 different raw materials, including copper. The information available starts on January 1960. The prediction of prices from September 2018 to August 2019 showed a root mean squared error (RMSE) value of 318.7996, a mean absolute percentage error (MAPE) of 0.0418 and a mean absolute error (MAE) of 252.8567. The main strengths of the proposed algorithm are two-fold. On the one hand, it can be applied in a systematic way and the results are obtained without any human with expert knowledge having to take any decision; on the other hand, all the trained models are MARS. This means that the models are equations that can be read and understood, and not black box models like artificial neural networks.

[1]  José Luís Calvo-Rolle,et al.  A New Missing Data Imputation Algorithm Applied to Electrical Data Loggers , 2015, Sensors.

[2]  P. J. García Nieto,et al.  Non-linear numerical analysis of a double-threaded titanium alloy dental implant by FEM , 2008, Appl. Math. Comput..

[3]  Bruce R. Kowalski,et al.  MARS: A tutorial , 1992 .

[4]  Francisco Javier de Cos Juez,et al.  A Hybrid Device of Self Organizing Maps (SOM) and Multivariate Adaptive Regression Splines (MARS) for the Forecasting of Firms’ Bankruptcy , 2011 .

[5]  Alicja Krzemień,et al.  Investment in new tungsten mining projects , 2015 .

[6]  Francisco Javier de Cos Juez,et al.  An ANN-Based Smart Tomographic Reconstructor in a Dynamic Environment , 2012, Sensors.

[7]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[8]  Gillian Dooley,et al.  An assessment of time series methods in metal price forecasting , 2005 .

[9]  J. Tilton,et al.  Assessing the long-run availability of copper , 2007 .

[10]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[11]  David J. Parsons,et al.  An improved wavelet–ARIMA approach for forecasting metal prices , 2014 .

[12]  Francisco Javier de Cos Juez,et al.  A hybrid ARIMA-SVM model for the study of the remaining useful life of aircraft engines , 2019, J. Comput. Appl. Math..

[13]  F. J. D. C. Juez,et al.  Forecasting the COMEX copper spot price by means of neural networks and ARIMA models , 2015 .

[14]  Weimin Ma,et al.  Forecasting iron ore import and consumption of China using grey model optimized by particle swarm optimization algorithm , 2013 .

[15]  P. J. García Nieto,et al.  PM10 concentration forecasting in the metropolitan area of Oviedo (Northern Spain) using models based on SVM, MLP, VARMA and ARIMA: A case study. , 2018, The Science of the total environment.

[16]  Constantine Frangakis,et al.  Multiple imputation by chained equations: what is it and how does it work? , 2011, International journal of methods in psychiatric research.

[17]  Stef van Buuren,et al.  MICE: Multivariate Imputation by Chained Equations in R , 2011 .

[18]  Alicja Krzemień,et al.  Rare earth elements price forecasting by means of transgenic time series developed with ARIMA models , 2018, Resources Policy.

[19]  Alicja Krzemień,et al.  Fire risk prevention in underground coal gasification (UCG) within active mines: Temperature forecast by means of MARS models , 2019, Energy.

[20]  F. Las-Heras,et al.  Efectos de la crisis económica en la demanda por trastornos mentales en Asturias: datos del Registro Acumulativo de Casos Psiquiátricos (2000-2010) , 2014 .

[21]  Alicja Krzemień,et al.  Forecasting European thermal coal spot prices , 2015, Journal of Sustainable Mining.

[22]  Mehdi Khashei,et al.  An artificial neural network (p, d, q) model for timeseries forecasting , 2010, Expert Syst. Appl..

[23]  P. J. García Nieto,et al.  Study of cyanotoxins presence from experimental cyanobacteria concentrations using a new data mining methodology based on multivariate adaptive regression splines in Trasona reservoir (Northern Spain). , 2011 .