Abstract—This research proposes time series forecasting of commodity prices by using multiresolution analysis from wavelet transform. In this work, discrete wavelet transform based multiresolution decomposition of Deubechies family is used. Firstly, Deubechies wavelet transform is applied to the training set of time series data up to level four. The reconstruction values of the approximation part of wavelet from each level are then used for the forecasting process by ARIMA model. The validation set of data is used to analyze and select the best model from all 4 levels of multiresolution decomposition. Finally, best selected validating model is used for evaluating the remaining testing data set. The forecasting results by using multiresolution analysis are compared to the case where the original data are directly modeled and forecasted by ARIMA. Results based on the mean absolute percentage error evaluation from using multiresolution analysis are better for both of the two studied data including daily gold price and rubber price. By applying multiresolution analysis, the improvement is 10.83% for gold price and 42.68% for rubber price. The variances of errors from the proposed method on both data sets are also much less than directly use the original time series data for forecasting.
Index Terms—Multiresolution analysis, wavelet transform, commodity prices, time series forecasting.
The authors are with the School of Computer Engineering, SUT, 111 University Avenue, Muang, Nakhon Ratchasima 30000, Thailand (corresponding author: Supaporn Bunrit; tel.: +66944961244; e-mail: sbunrit@sut.ac.th, nittaya@sut.ac.th, kerdpras@sut.ac.th).
Cite: Supaporn Bunrit, Nittaya Kerdprasop, and Kittisak Kerdprasop, "Multiresolution Analysis Based on Wavelet Transform for Commodity Prices Time Series Forecasting," International Journal of Machine Learning and Computing vol. 8, no. 2, pp. 175-180, 2018.