Aplicação de Machine learning e séries temporais para previsão de demanda: um estudo de caso em uma empresa de bens de consumo
DOI:
https://doi.org/10.34117/bjdv9n8-001Keywords:
planejamento de demanda, previsão de vendas, sales and operations planning, preverAbstract
O objetivo deste trabalho é impulsionar a acuracidade da previsão de demanda de uma empresa de bens de consumo, através da implementação de modelos de séries temporais e “machine learning” Metodologia: Para tal, foram coletados os históricos de vendas da empresa num horizonte de cinco anos, posteriormente foi realizado uma análise exploratória de dados, realizada a limpeza dos outliers, treinados diversos modelos de séries temporais e “machine learning”, testados os resultados de acuracidade, e selecionado o melhor modelo para cada produto para se realizar a previsão de demanda Resultados: Obteve-se uma redução no erro médio da previsão de vendas em 19 pontos percentuais, o que possibilitou redução de estoque de 21% e aumento no nível de serviço ao cliente em 7%. Limitações: A pesquisa focou na primeira fase do processo de S&OP que consiste em prever demanda. Neste estudo focou-se em aplicação de métodos de séries temporais de Machine learning para aumentar a acuracidade deste processo. Implicações Práticas: Comprovou-se, dessa forma, que os modelos de séries temporais e “machine learning” possuem resultados significativamente mais atraentes no processo de planejamento de demanda do que modelos simples de médias móveis e suavizações. Originalidade: A partir de revisão de literatura, percebe-se que ainda há um gap de estudos aplicando métodos de séries temporais e Machine learning no processo de S&OP, dessa forma essa pesquisa busca impulsionar sua aplicação através dos resultados obtidos.
References
APICS.2018. Certified in Production and Inventory Management: Learning System. APICS, Chicago.
Ben Ali, M., D’Amours, S. , Gaudreault, J. et al. (2019), "Integrating revenue management and sales and operations planning in a Make-To-Stock environment: softwood lumber case study", INFOR: Information Systems and Operational Research, Taylor & Francis, Vol. 57, No. 2, pp. 314-41. http://dx.doi.org/10.1080/03155986.2018.1554420.
Boser, B.E., Guyon, I.M. and Vapnik, V.N., 1992, July. A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory (pp. 144-152).
Büttner, D., Rabe, M., 2021. "sales forecasting in the electrical industry - an illustrative comparison of time series and machine learning approaches," 2021 9th international conference on traffic and logistic engineering (ictle)
Cadavid J.P.U, Iamouri S., Grabot B. 2018. Trends in Machine Learning Applied to Demand & Sales Forecasting: A Review. International Conference on Information Systems, Logistics and Supply Chain
Coelho, L., Richert, W. 2015.Building Machine Learning Systems with Python. Packt Publishing Ltd
Chen, I.F. and Lu, C.J., 2017. Sales forecasting by combining clustering and machine-learning techniques for computer retailing. Neural Computing and Applications, 28, pp.2633-2647.
Christopher, M. 2011. Logistics and Supply Chain Management, 4th edition. Financial Times Prentice Hall, Harlow
Fix, E., 1985. Discriminatory analysis: nonparametric discrimination, consistency properties (Vol. 1). USAF school of Aviation Medicine.
Forsyth, D.A., Mundy, J.L., di Gesú, V., Cipolla, R., LeCun, Y., Haffner, P., Bottou, L. and Bengio, Y., 1999. Object recognition with gradient-based learning. Shape, contour and grouping in computer vision, pp.319-345.
Goh, S.H. and Eldridge, S. (2019), "Sales and Operations Planning: The effect of coordination mechanisms on supply chain performance", International Journal of Production Economics, Vol. 214, pp. 80-94. http://dx.doi.org/10.1016/j.ijpe.2019.03.027.
Grimson, J.A. and D.F. Pyke, Sales and operations planning: an exploratory study and framework. The International Journal of Logistics Management, 2007.
Ho, T.K., 1995, August. Random decision forests. In Proceedings of 3rd international conference on document analysis and recognition (Vol. 1, pp. 278-282). IEEE.
Hochreiter, S. and Schmidhuber, J., 1997. Long short-term memory. Neural computation, 9(8), pp.1735-1780.
Huang, G., Huang, G.B., Song, S. and You, K., 2015. Trends in extreme learning machines: A review. Neural Networks, 61, pp.32-48.
Hunt, E.B., Marin, J. and Stone, P.J., 1966. Experiments in induction.
James, G., Witten, D., Hastie, T. and Tibshirani, R., 2013. An introduction to statistical learning (Vol. 112, p. 18). New York: springer.
Kwak, Sang & Kim, Jong. 2017. Statistical data preparation: Management of missing values and outliers. Korean Journal of Anesthesiology
Kjellsdotter Ivert, L. K. et al. (2015a), “Sales and operations planning: responding to the needs of industrial food produ-cers”, Production Planning & Control, Vol. 26, pp. 280-295.
Kohonen, T., 1982. Self-organized formation of topologically correct feature maps. Biological cybernetics, 43(1), pp.59-69.
Kristensen, J. and P. Jonsson, Context-based sales and operations planning (S&OP) research. International Journal of Physical Distribution & Logistics Management, 2018. 48(1): p. 19-46.
Lapide, L. (2004), “Sales and Operations Planning Part I: The Process”, The Journal of Business Forecasting, Fall-2004, pp. 17-19.
Lim, L.L., Alpan, G. and Penz, B. (2017), "A simulation-optimization approach for sales and operations planning in build-to-order industries with distant sourcing: Focus on the automotive industry", Computers & Industrial Engineering, Vol. 112, pp. 469-82. http://dx.doi.org/10.1016/j.cie.2016.12.002.
Mishra, D., Gunasekaran, A., Papadopoulos, T. et al.(2016), "Big Data and Supply Chain Management: a review and bibliometric analysis", Annals of Operations Research, Vol. 270, No. 1-2, pp. 313-36. http://dx.doi.org/10.1007/s10479-016-2236-y.
Oliva, R., Watson, N. 2011. Cross-functional alignment in supply chain planning: a case study of sales and operations planning, Journal of Operations Management, Vol. 29 No. 5
Nicolas, F.N.P., Thomé, A.M.T. and Hellingrath, B., 2021. Usage of information technology and business analytics within sales and operations planning: a systematic literature review. Brazilian Journal of Operations & Production Management, 18(3), pp.1-15
Papacharalampous, G., Tyralis, H. and Koutsoyiannis, D., 2018. Univariate time series forecasting of temperature and precipitation with a focus on machine learning algorithms: A multiple-case study from Greece. Water resources management, 32(15), pp.5207-5239.
Pavlyshenko, B.M., 2019. Machine-learning models for sales time series forecasting. Data, 4(1), p.15.
Pedroso, C.B., A.L. da Silva, and W.L. Tate, Sales and Operations Planning (S&OP): Insights from a multi-case study of Brazilian Organizations. International Journal of Production Economics, 2016. 182: p. 213-229
Ohlson, N.-E., J. Bäckstrand, and M. Riveiro, Artificial Intelligence-enhanced Sales & Operations Planning in an Engineer-to-order context, in PLAN Utvecklings konferens 2021. 2021: Borås
Rumelhart, D.E., Hinton, G.E. and Williams, R.J., 1986. Learning representations by back-propagating errors. nature, 323(6088), pp.533-536.
Scavarda, L.F., Hellingrath, B., Kreuter, T., Thomé, A.M.T., Seeling, M.X., Fischer, J.H. and Mello, R., 2017. A case method for Sales and Operations Planning: a learning experience from Germany. Production, 27.
Schmidt, A., Kabir, M.W.U. and Hoque, M.T., 2022. Machine learning based restaurant sales forecasting. Machine Learning and Knowledge Extraction, 4(1), pp.105-130.
Seeling, M.X., Scavarda, L.F. and Thomé, A.M.T., 2019. A sales and operations planning application in the Brazilian subsidiary of a multinational chemical company. Brazilian Journal of Operations & Production Management, 16(3), pp.424-435.
Sherstinsky, A., 2020. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 404, p.132306.
Thomassey, S., 2010. Sales forecasts in clothing industry: The key success factor of the supply chain management. International Journal of Production Economics, 128(2), pp.470-483.
Thomé, A. M. T. et al. (2012a), “Sales and Operations Plan-ning: a research synthesis”, International Journal of Produc-tion Economics, Vol. 138, No. 1, pp. 1-13.
Tugay, Resul and Şule Gündüz Öğüdücü. 2017. “Demand Prediction using Machine Learning Methods and Stacked Generalization.”
Wallace, T.F.; Stahl, R.A. 2003. Previsão de Vendas: uma nova abordagem. Trad: Daniel Gasnier. São Paulo: IMAM
