Title :
Evolving fuzzy linear regression tree approach for forecasting sales volume of petroleum products
Author :
Lemos, Andre ; Leite, Daniel ; Maciel, Leandro ; Ballini, Rosangela ; Caminhas, Walmir ; Gomide, Fernando
Author_Institution :
Dept. of Electron. Eng., Fed. Univ. of Minas Gerais, Belo Horizonte, Brazil
Abstract :
The 2012 FUZZ-IEEE conference competition “Learning Fuzzy Systems from Data” aims to establish the empirical accuracy of fuzzy forecasting algorithms in the domain of prediction of the sales volume of petroleum products. Currently, there are no guidelines or consensus on a best practice methodology. This paper proposes evolving fuzzy linear regression trees (eFT) to extract from both, daily prices and past sales volume data, information of interest to attain accurate forecasts of the next day sales. Essentially, eFT attempts to find spatio-temporal correlations from a historical perspective of competitors´ prices and previous sales. A dimension reduction method based on the least angle regression (LARS) algorithm is considered for input variable selection. Computational experiments show that the eFT predictor using LARS is an effective approach to nonlinear time series forecasting providing encouraging results in the competition scenario.
Keywords :
competitive algorithms; correlation theory; economic forecasting; fuzzy set theory; petroleum; regression analysis; time series; trees (mathematics); 2012 FUZZ-IEEE conference competition; LARS algorithm; competitors prices; daily prices; dimension reduction method; eFT predictor; fuzzy forecasting algorithms; fuzzy linear regression trees; input variable selection; learning fuzzy systems from data; least angle regression algorithm; next day sales; nonlinear time series forecasting; past sales volume data; petroleum products; prediction domain; sales volume forecasting; spatio-temporal correlations; Computational modeling; Data models; Forecasting; Input variables; Linear regression; Marketing and sales; Petroleum;
Conference_Titel :
Fuzzy Systems (FUZZ-IEEE), 2012 IEEE International Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1507-4
Electronic_ISBN :
1098-7584
DOI :
10.1109/FUZZ-IEEE.2012.6250809