Abstract
In this study, we address a real sales forecasting problem of a multinational fashion retailer. The fashion retailer has been operating retail stores and warehouses in a major Asian city for decades. The volume of daily sales of each stock kee** unit in this city needs to be determined to develop an effective and efficient inventory and logistics system for the retailer. Based on complicated real sales data sets, we use a minimum description length neural network (MDL-NN) which searches for the optimal model size to predict this value. In order to address the problem of intermittent sales data and zero actual sales, we propose a revised mean absolute percentage error (RMAPE) measurement for performance evaluation. Our experimental results show that for most test data sets, the evaluation results based on RMAPE are consistent with those based on two other established measurements, the symmetric mean average percentage error and mean absolute scaled error. Specifically, on all three performance indicators, the MDL-NN method achieves a smaller error than almost all other commonly used sales forecasting methods on almost all test data sets. Finally, we examine the gap between the performance indicators between the forecasting result values in decimal format, which are directly generated by the forecasting methods, and the forecasting result values in integer format, which are rounded off from the decimal numbers. Our findings indicate that this gap is not trivial and should not be ignored.
Similar content being viewed by others
References
Nenni ME, Giustiniano L, Pirolo L (2013) Demand forecasting in the fashion industry: a review. Int J Eng Bus Manag 5(37):1–6
Varghese V, Rossetti M (2008) A parametric bootstrap** approach to forecast intermittent demand. In: Proceedings of the 2008 industrial engineering research conference (2008)
Ren S, Choi TM, Liu N (2015) Fashion sales forecasting with a panel data-based particle-filter model. IEEE Trans Syst Man Cybern Syst 45(3):411–421
Cherkassky V, Mulier FM (2007) Learning from data: concepts, theory, and methods. Wiley, New York
Bartlett PL (1997) For valid generalization, the size of the weights is more important than the size. Adv Neural Inf Process Syst 9:134
Au K-F, Choi T-M, Yong Yu (2008) Fashion retail forecasting by evolutionary neural networks. Int J Prod Econ 114(2):615–630
Small M, Tse CK (2002) Minimum description length neural networks for time series prediction. Phys Rev E 66(6):066701
Liu N, Ren S, Choi TM, Hui CL, Ng SF (2013) Sales forecasting for fashion retailing service industry: a review”. Math Problems Eng. https://doi.org/10.1155/2013/738675
Stevenson WJ, Hojati M (2007) Operations management, Chapter 3, vol 8. McGraw-Hill/Irwin, Boston
Winters PR (1960) Forecasting sales by exponentially weighted moving averages. Manag Sci 6(3):324–342
Sun Z-L et al (2008) “Sales forecasting using extreme learning machine with applications in fashion retailing. Decis Support Syst 46(1):411–419
**a M et al (2012) Fashion retailing forecasting based on extreme learning machine with adaptive metrics of inputs. Knowl Based Syst 36:253–259
Yelland PM, Dong X (2014) Forecasting demand for fashion goods: a hierarchical Bayesian approach. In: Choi TM, Hui CL, Yu Y (eds) Intelligent fashion forecasting systems: models and applications. Springer, Berlin, Heidelberg, pp 71–94
Hui C-L et al (2005) Learning-based fuzzy colour prediction system for more effective apparel design. Int J Cloth Sci Technol 17(5):335–348
Thomassey S (2014) Sales forecasting in apparel and fashion industry: a review. In: Intelligent fashion forecasting systems: models and applications. Springer, Berlin, pp 9–27
Choi TM, Hui CL, Liu N, Ng SF, Yu Y (2014) Fast fashion sales forecasting with limited data and time. Decis Support Syst 59:84–92
Homassey S (2010) Sales forecasts in clothing industry: the key success factor of the supply chain management. Int J Prod Econ 128(2):470–483
Rissanen J (1978) Modeling by shortest data description. Automatica 14(5):465–471
Chong J-K, Ho T-H, Tang CS (2001) A modeling framework for category assortment planning. Manuf Serv Oper Manag 3(3):191–210
Choi T-M, Yong Yu, Kin-Fan A (2011) A hybrid SARIMA wavelet transform method for sales forecasting. Decis Support Syst 51(1):130–140
Wong WK, Guo ZX (2010) A hybrid intelligent model for medium-term sales forecasting in fashion retail supply chains using extreme learning machine and harmony search algorithm. Int J Prod Econ 128(2):614–624
Choi T-M et al (2012) Color trend forecasting of fashionable products with very few historical data. IEEE Trans Syst Man Cybern Part C: Appl Rev 42(6):1003–1010
Judd K, Mees A (1995) On selecting models for nonlinear time series. Physica D 82(4):426–444
Deng J-L (1989) Introduction to grey system theory. J Grey Syst 1(1):1–24
Hsu CC, Chen CY (2003) Applications of improved grey prediction model for power demand forecasting. Energy Conv Manag 44(14):2241–2249
Huang G-B, Zhu Q-Y, Siew C-K (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. In: 2004 IEEE international joint conference on neural networks, 2004. Proceedings. vol. 2. IEEE (2004)
Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST) 2(3):27
Hamilton JD (1989) A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica 57:357–384
Li D Retrieved 12/5, 2014 from http://www.ntu.edu.sg/home/egbhuang/elm_codes.html
DML-NN source code. Retrieved 12/6, 2014
Funding
Funding was provided by National Natural Science Foundation of China (Grant No. 71531009).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, P., Ming, W. & Hu, B. Sales forecasting in rapid market changes using a minimum description length neural network. Neural Comput & Applic 33, 937–948 (2021). https://doi.org/10.1007/s00521-020-05294-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05294-8