Title: Sales forecasting of a dairy product manufacturing company: a comparative study of autoregressive integrated moving average and local linear neuro-fuzzy models
Authors: Babak H. Tabrizi; Seyed Farid Ghaderi
Addresses: School of Industrial Engineering, College of Engineering, University of Tehran, P.O. Box 11155-4563, Tehran, Iran ' School of Industrial Engineering, College of Engineering, University of Tehran, P.O. Box 11155-4563, Tehran, Iran
Abstract: In today's competitive world, accurate sales forecasting is crucially required for manufacturing organisations as it can play a remarkable role in reducing their costs and increasing their profits, consequently. Moreover, having a clear knowledge about the future sales value of the organisation can be accompanied by better customer service, reduced lost sales and product returns, and more capable production planning. The issue can be highlighted for dairy products much more as their life cycle is limited and their quality is highly associated with consumers' health. Therefore, the problem has been addressed in this paper by applying autoregressive integrated moving average and local linear neurofuzzy models. The models' performance is compared with respect to a case study carried out in a dairy product manufacturing company in Iran. Through the experimental results, the local linear neurofuzzy model proved well and could outperform the other method. Finally, the future trend of the short-term sale is forecasted for the given company.
Keywords: sales forecasting; dairy products; autoregressive integrated moving average; ARIMA; locally linear neuro-fuzzy; LLNF modelling; neural networks; fuzzy logic; Iran; short-term sales.
DOI: 10.1504/IJSOM.2016.077787
International Journal of Services and Operations Management, 2016 Vol.24 No.4, pp.531 - 547
Received: 13 Nov 2014
Accepted: 22 Jan 2015
Published online: 15 Jul 2016 *