Compare the forecasting method of artificial neural network and support vector regression model to measure the bullwhip effect in supply chain

E. Fradinata; S. Suthummanon; W. Suntiamorntut; Muhamad Mat Noor

doi:10.15282/jmes.13.2.2019.04.0401

Authors

E. Fradinata Industrial Engineering, Syiah Kuala University, Banda Aceh 23111, Indonesia Phone/Fax: 062-0651-7552222
S. Suthummanon Department of Industrial Engineering, Prince of Songkla University, Hatyai, Thailand
W. Suntiamorntut Computer Engineering, Prince of Songkla University, Hatyai, Thailand
Muhamad Mat Noor Faculty of Mechanical & Manufacturing Engineering, Universiti Malaysia Pahang (UMP), Malaysia

DOI:

https://doi.org/10.15282/jmes.13.2.2019.04.0401

Keywords:

artificial neural network, support vector regression, supply chain

Abstract

The objective of this study was to compare the Bullwhip Effect (BWE) in the supply chain through two methods and to determine the inventory policy for the uncertainty demand. It would be useful to determine the best forecasting method to predict the certain condition. The two methods are Artificial Neural Network (ANN) and Support Vector Regression (SVR), which would be applied in this study. The data was obtained from the instant noodle dataset where it was in random normal distribution. The forecasting demands signal have Mean Squared Error (MSE) where it is used to measure the bullwhip effect in the supply chain member. The magnification of order among the member of the supply chain would influence the inventory. It is quite important to understand forecasting techniques and the bullwhip effect for the warehouse manager to manage the inventory in the warehouse, especially in probabilistic demand of the customer. This process determines the appropriate inventory policy for the retailer. The result from this study shows that ANN and SVR have the variance of 0.00491 and 0.07703, the MSE was 1.55e^-6 and 1.53e^-2, and the total BWE was 95.61 and 1237.19 respectively. It concluded that the ANN has a smaller variance than SVR, therefore, the ANN has a better performance than SVR, and the ANN has smaller BWE than SVR. At last, the inventory policy was determined with the continuous review policy for the uncertainty demand in the supply chain member.

References

Gunn SR. Support vector machines for classification and regression. ISIS Technical Report 1998; 14(1):5-16.

Chopra S, Meindl P. Supply chain management. Strategy, planning & operation. Das summa summarum des management. Springer 2007;265-275.

Lee HL, Padmanabhan V, Whang S. The bullwhip effect in supply chains. MIT Sloan Management Review 1997; 38(3):93.

Lee HL, Padmanabhan V, Whang S. Information distortion in a supply chain: The bullwhip effect. Management science 2004; 50(12_supplement):1875-1886.

Gupta A, Maranas CD, McDonald CM. Mid-term supply chain planning under demand uncertainty: customer demand satisfaction and inventory management. Computers & Chemical Engineering 2000; 24(12):2613-2621.

Meinel LA, Stolpen AH, Berbaum KS, Fajardo LL, Reinhardt JM. Breast MRI lesion classification: Improved performance of human readers with a backpropagation neural network computer‐aided diagnosis (CAD) system. Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine 2007; 25(1):89-95.

He X, Xu S. Artificial neural networks. Process Neural Networks: Theory and Applications 2010;20-42.

Jaliliantabar F, Ghobadian B, Najafi G, Yusaf T. Artificial neural network modeling and sensitivity analysis of performance and emissions in a compression ignition engine using biodiesel fuel. Energies 2018; 11(9).

Sakinah MH, Amirruddin AK, Kadirgama K, Ramasamy D, Rahman MM, Noor MM. The application of response surface methodology in the investigation of the tribological behavior of palm cooking oil blended in engine oil. Advances in Tribology 2016.

Rahman MM, Kadirgama K, Noor MM, Ramasamy D. Optimization of abrasive machining of ductile cast iron using TiO2 nanoparticles: A multilayer perceptron approach’ ARPN Journal of Engineering and Applied Sciences 2016; 11(4):2529-2534.

Najiha MS, Rahman MM, Kadirgama K, Noor MM, Ramasamy D. Multi-objective optimization of minimum quantity lubrication in end milling of aluminum alloy AA6061T6. International Journal of Automotive and Mechanical Engineering 2015; 12(1):3003-3017.

Hecht-Nielsen R. Theory of the backpropagation neural network. Neural networks for perception Elsevier 1992;65-93.

Cortes C, Vapnik V. Support-vector networks. Machine learning 1995; 20(3):273-297.

Drucker H, Burges CJ, Kaufman L, Smola AJ, Vapnik V. Support vector regression machines. in Editor (Ed.)^(Eds.): Book Support vector regression machines 1997. Edn.155-161.

Kleijnen JP, Smits MT Performance metrics in supply chain management. Journal of the operational research society 2003; 54(5):507-514.

Cachon GP, Fisher M. Supply chain inventory management and the value of shared information. Management science 2000; 46(8):1032-1048.

Bowers MR, Agarwal A. Lower In-Process Inventories and Better On-Time Performance at Tanner Companies. Inc’ Interfaces 1995; 25(4):30-43.

Cachon GP, Zipkin PH. Competitive and cooperative inventory policies in a two-stage supply chain. Management science 1999; 45(7):936-953.

Jaipuria S, Mahapatra S. An improved demand forecasting method to reduce bullwhip effect in supply chains. Expert Systems with Applications 2014; 41(5):2395-2408.

Moreno‐Barón L, Cartas R, Merkoçi A, Alegret S, Gutiérrez JM, Leija L, Hernandez PR, Munoz R, del Valle M. Data compression for a voltammetric electronic tongue modelled with artificial neural networks. Analytical letters 2005; 38(13):2189-2206.

Buchmeister B, Pavlinjek J, Palcic I, Polajnar A. Bullwhip effect problem in supply chains. Advances in production engineering & management 2008; 3(1):45-55.

Mendoza A, Ventura JA. A serial inventory system with supplier selection and order quantity allocation. European Journal of Operational Research 2010; 207(3):1304-1315.

Liu P, Chen S-H, Yang H-H, Hung C-T, Tsai M-R. Application of artificial neural network and SARIMA in portland cement supply chain to forecast demand. in Editor (Ed.)^(Eds.): ‘Book Application of artificial neural network and SARIMA in portland cement supply chain to forecast demand IEEE 2008;edn;97-101.

Buurman J. Supply chain logistics management. McGraw-Hill 2002.

Guiso L, Sapienza P, Zingales L. Trusting the stock market. the Journal of Finance 2008; 63(6):2557-2600.

Lai G, Debo LG, Sycara K. Sharing inventory risk in the supply chain: The implication of financial constraint. Omega 2009; 37(4):811-825.

Kristianto Y, Ajmal MM, Sandhu M. Adopting TQM approach to achieve customer satisfaction: A flour milling company case study. The TQM Journal 2012; 24(1):29-46.

Cachon GP. The allocation of inventory risk in a supply chain: Push, pull, and advance-purchase discount contracts. Management science 2004; 50(2):222-238.

Lee HL, Padmanabhan V, Whang S. Information distortion in a supply chain: The bullwhip effect. Management science 1997; 43(4):546-558.

Chan L, Simchi-Levi D, Swann J. Effective dynamic pricing strategies with stochastic demand. Massachusetts Institute of Technology Cambridge MA, 2001.

Andrew-Munot M, Yassin A, Shazali S, Sawawi M, Tanjong S, Razali N. Analysis of production planning activities in remanufacturing system. Journal of Mechanical Engineering & Sciences 2018; 12(2):3548-3565.

Mojaveri HR, Mousavi SS, Heydar M, Aminian A. Validation and selection between machine learning technique and traditional methods to reduce bullwhip effects: a data mining approach. World Academy of Science Engineering and Technology 2009; 25.

Hanief M, Wani M. Artificial neural network and regression-based models for prediction of surface roughness during turning of red brass (C23000). Journal of Mechanical Engineering & Sciences 2016; 10:1835-1845.

Rajasekaran S, Gayathri S, Lee T-L. Support vector regression methodology for storm surge predictions. Ocean Engineering 2008; 35(16):1578-1587.

Shi SM, Da Xu L, Liu B. Improving the accuracy of nonlinear combined forecasting using neural networks. Expert Systems with Applications 1999; 16(1):49-54.

Widrow B, Hoff ME. Adaptive switching circuits’, in Editor (Ed.)^(Eds.): ‘Book Adaptive switching circuits. Stanford Univ Ca Stanford Electronics Labs 1960;22

Block H-D. The perceptron: A model for brain functioning. i. Reviews of Modern Physics 1962; 34(1):123.

Razak N, Rahman MM, Noor MM, Kadirgama K. Artificial intelligence techniques for machining performance: A review. In Editor (Ed.)^(Eds.): ‘Book Artificial intelligence techniques for machining performance: A review 2010;3-4.

Noor CWM, Mamat R, Najafi G, Yasin MHM, Ihsan CK, Noor MM. Prediction of marine diesel engine performance by using artificial neural network model. Journal of Mechanical Engineering and Sciences 2016; 10(1):1917-1930.

Fradinata E, Suthummanon S, Suntiamorntut W. Forecasting determinant of cement demand in Indonesia with artificial neural network. Journal of Asian Scientific Research 2015;5(7):373-384.

Noor MM, Kadirgama K, Rejab M, Rahman MM, Bakar RA, Ismail H. Artificial Intelligent Model to Predict Surface Roughness in Laser Machining. In Editor (Ed.)^(Eds.): ‘Book Artificial Intelligent Model to Predict Surface Roughness in Laser Machining 2009;edn:1-3.

Basak D, Pal S, Patranabis DC. Support vector regression. Neural Information Processing-Letters and Reviews 2007;11(10):203-224.

Santosa B. Data mining teknik pemanfaatan data untuk keperluan bisnis 2007. 1st ed. Yogyakarta: Graha Ilmu, 2007.

Braga PL, Oliveira AL, Meira SR. A GA-based feature selection and parameters optimization for support vector regression applied to software effort estimation. in Editor (Ed.)^(Eds.): Book A GA-based feature selection and parameters optimization for support vector regression applied to software effort estimation (ACM) 2008;edn:1788-1792.

Huang Q, Mao J, Liu Y. An improved grid search algorithm of SVR parameters optimization. in Editor (Ed.)^(Eds.): ‘Book An improved grid search algorithm of SVR parameters optimization IEEE 2012;edn:1022-1026.

Müller K-R, Smola AJ, Rätsch G, Schölkopf B, Kohlmorgen J, Vapnik V. Predicting time series with support vector machines. in Editor (Ed.)^(Eds.): ‘Book Predicting time series with support vector machines. Springer 1997; edn: 999-1004.

Hsu C-C, Wu C-H, Chen S-C, Peng K-L. Dynamically optimizing parameters in support vector regression: An application of electricity load forecasting. in Editor (Ed.)^(Eds.): Book Dynamically optimizing parameters in support vector regression: An application of electricity load forecasting. IEEE 2006;edn:30c-30c.

Fradinata E, Suthummanon S, Sunthiamorntut W. Comparison of hybrid ANN models: A case study of instant noodle industry in Indonesia. International journal of advanced and applied sciences 2017; 4(8):19-28.

Simchi-Levi D, Simchi-Levi E, Kaminsky P. Designing and managing the supply chain: Concepts, strategies, and cases. 3rd edition. McGraw-Hill Book Company. New York 1999.

Chan LM, Shen ZM, Simchi-Levi D, Swann JL. Coordination of pricing and inventory decisions: A survey and classification. Handbook of quantitative supply chain analysis Springer, Toronto 2004:335-392.

Pujawan IN. The effect of lot sizing rules on order variability. European Journal of Operational Research 2004;159(3):617-635.