Reduction of Bullwhip Effect in Supply Chain through Improved Forecasting Method: An Integrated DWT and SVM Approach

Autor:	Siba Sankar Mahapatra, Sanjita Jaipuria
Rok vydání:	2013
Předmět:	Reduction (complexity) Support vector machine Data set Computer science Supply chain Bullwhip effect Wavelet transform Autoregressive integrated moving average Data mining Demand forecasting computer.software_genre computer Simulation
Zdroj:	Swarm, Evolutionary, and Memetic Computing ISBN: 9783319037554 SEMCCO (2)
DOI:	10.1007/978-3-319-03756-1_7
Popis:	In a supply chain, forecasting method directly influences the bullwhip effect (BWE) and net-stock amplification (NSAmp) which adversely impact on performance of supply chain. However, such adverse effects can be moderated through use of realistic and accurate demand forecasting models. In the present study, an integrated approach of discrete wavelet transforms (DWT) analysis and least-square support vector machine (LSSVM) is proposed for demand forecasting. Initially, the proposed DWT-LSSVM model is tested and validated using a data set from open literature. A comparative study between Autoregressive Integrated Moving Average (ARIMA) and proposed model has been made. Further, the model is tested with demand data collected from two different manufacturing firms. It is observed that proposed model outperforms ARIMA model in respect to accurate estimation of demand and reduce BWE.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::af78f6f037899fd39806b8cfae2b9990 https://doi.org/10.1007/978-3-319-03756-1_7 Zobrazit plný text záznamu