FORECASTING INTERMITTENT DEMAND WITH ARTIFICIAL NEURAL NETWORKS METHOD

Yıl 2016, Cilt: 4 Sayı: 1, 1 - 32, 01.06.2016

Derya Saatçioğlu Necdet Özçakar

https://doi.org/10.14514/BYK.m.21478082.2016.4/1.1-32

Cited By: 3

Öz

Forecasting and accuracy of demand has a direct effect in the success of a business and customer satisfaction. Whereas many methods show successful results in forecasting and planning demand of products with smooth demand, they fail with products that have many time periods with zero demands. Variability of capacity and pattern of demand causes forecasting and planning of it to become difficult. In this study, for forecasting intermittent demand, Croston Method and Multilayer Perceptron which is also an artificial neural network have been analyzed. These methods have been used for forecasting intermittent demand in one of the categories of a business that operates in e-trade sector. Afterwards, performance of each method has been compared using appropriate accuracy measures

Anahtar Kelimeler

Intermittent demand, multilayer perceptron, artificial neural networks

YAPAY SİNİR AĞLARI YÖNTEMİ İLE ARALIKLI TALEP TAHMİNİ

Öz

Talep tahmini ve doğruluğunun bir işletmenin başarısına ve müşteri memnuniyetine doğrudan etkisi bulunmaktadır. Düzgün talep yapısına sahip ürünlerin talep tahmini ve planlamasında birçok yöntem başarılı sonuçlar verirken çoğu zaman diliminde sıfır talep gören aralıklı talep yapısına sahip ürünlerin talep tahmininde başarılı olamamaktadır. Talep büyüklüğünün ve şeklinin değişkenliği bu ürünler için talep tahmini ve planlamanın yapılmasını zorlaştırmaktadır. Bu çalışmasında, aralıklı talep yapısına sahip ürünlerin talep tahminini için Croston yöntemi ve bir yapay sinir ağı modeli olan Çok Katmanlı Algılayıcılar incelenmiştir. Bu yöntemler e-ticaret sektöründe faaliyet gösteren bir işletmenin satış yaptığı bir kategorideki aralıklı talep yapısına sahip ürünlerinin talep tahmini için kullanılmıştır. Daha sonra her bir yöntemin performansı uygun ölçütler kullanılarak ölçülmüştür

Anahtar Kelimeler

Aralıklı talep, çok katmanlı algılayıcılar, yapay sinir ağları

Kaynakça

• Altay, Nezih, Frank Rudisill ve Lewis A. Litteral (2008) “Adapting Wright’s Modification of Holt’s Method to Forecasting Intermittent Demand”, International Journal of Production Economics, 111(2), s.389-408.
• Alpaydın, Ethem (2012) Yapay Öğrenme, 2. Baskı, İstanbul: Boğaziçi Üniversitesi.
• Akay, Diyar ve Mehmet Atak (2007) “Grey Prediction with Rolling Mechanism for Electricity Demand Forecasting of Turkey”, Energy, 32(9), s.1670-1675.
• Babai, Mohamed Z., Mohammad M. Ali ve Konstantinos Nikolopoulos (2012) “Impact of Temporal Aggregation on Stock Control Performance of Intermittent Demand Estimators: Empirical Analysis”, Omega, 40(6), s.713-721.
• Bao, Yukun, Wen Wang ve Jinlang Zhang (2004) “Forecasting Intermittent Demand by SVMs Regression”, IEEE International Conference on Systems Man and Cybernetics, s.461- 465.
• Basheer, Imad ve Maha Hajmeer (2000) “Artificial Neural Networks: Fundamentals, Computing, Design and Application”, Journal of Microbiological Methods, 43(1), s.3-31.
• Babiloni, Eugenia, Manuel Cardos, Jose M. Albarracin ve Marta E. Palmer (2010) “Demand Categorisation, Forecasting and Inventory Control for Intermittent Demand”, South African Journal of Industrial Engineering, 21(2), s.115-130.
• Bishop, Christopher M. (1995) Neural Networks for Pattern Recognition, Oxford: Clarendon.
• Boylan, John E. ve Aris A. Syntetos (2007) “The Accuracy of a Modified Croston Procedure”, International Journal of Production Economics, 107(2), s.511-517.
• Croston, J. D. (1972) “Forecasting and Stock Control for Intermittent Demand”, Journal of the Operational Research Society, 23(3), s.289-303.
• Eaves, Andrew H. ve Brian G. Kingsman (2004) “Forecasting for the Ordering and Stock- holding of Spare Parts”, Journal of the Operational Research Society, 55(4), s.431-437.
• Efron, Bradley (1979) “Bootsrap Method: Another Look at the Jackknife”, Annals of Statistics, 7(1), s.1-26.
• Elmas, Çetin (2010) Yapay Zekâ Uygulamaları, Ankara: Seçkin.
• Ghobbar, Adel A. ve Chris H. Friend (2003) “Evaluation of Forecasting Methods for Intermittent Parts Demand ın the Field of Aviation: A Predictive Model”, Computers & Operations Research, 30(14), s.2097-2114.
• Ghobbar, Adel A. ve Chris H. Friend (2002) “Sources of Intermittent Demand for Aircraft Spare Parts within Airline Operations”, Journal of Air Transport Management, 8(4), s.221- 231.
• Gutierrez, Rafael S., Adriano O. Solis ve Somnath Mukhopadhyay (2008) “Lumpy Demand Forecasting Using Neural Networks”, International Journal of Production Economics, 111(2), s.409-420.
• Hassoun, Mohamad (1995) Fundamentals of Artificial Neural Networks, New York: MIT.
• Haykin, Simon (1999) Neural Networks: A Comprehensive Foundation, 2. Baskı, Singapur: Prentice Hall.
• Heaton, Jeff (2008) Introduction to Neural Networks for C, Chesterfield: Heaton Research. Hua, Zhangsheng, Bin Zhang, Jie Yang ve D.S.Tan (2007) “A New Approach of Forecasting Intermittent Demand for Spare Parts Inventories in the Process Industries”, Journal of the Operational Research Society, 58(1), s.52-61.
• Hua, Zhangsheng ve Bin Zhang, (2006) “A Hybrid Support Vector Machines and Logistics Regression Approach for Forecasting Intermittent Demand of Spare Parts”, Applied Mathematics and Computation, 181(2), s.1035-1048.
• Hyndman, Rob J. ve Anne B. Koehler (2006) “Another Look at Measures of Forecast Accuracy”, International Journal of Forecasting, 22(4), s.679-688.
• Johnston, F. Roy, John E. Boylan ve Estelle A. Shale (2003) “An Examination of the Size of Orders from Customers, Their Characterisation and the Implications for Inventory Control of Slow Moving Items”, The Journal Of The Operational Research Society, 54(8), s.833- 837.
• Kasabov, Nikola K. (1996) Foundations of Neural Networks, Fuzzy Systems and Knowledge Engineering, London: MIT.
• Kourentzes, Nikolaos (2013) “Intermittent Demand Forecasts with Neural Networks”, International Journal of Production Economics, 143(1), s.198-206.
• Kostenko, Audrey V. ve Rob J. Hyndman (2006) “Viewpoint - A Note on the Demand Categorization of Demand Pattern”, Journal of the Operational Research Society, 57(10), s.1256-1258.
• Krenker, Andrej, Janez Bester ve Andrej Kos (2011) “Introduction To Artificial Neural Networks”, Artificial Neural Networks-Methodological Advances and Biomedical Applications içinde (der. K. Suzuki), InTech, s.3-19.
• Kriesel, David (2015) A Brief Introduction to Neural Networks, http://goo.gl/CpZ0QV, Erişim Tarihi: 27 Aralık 2015.
• Levén, Erik ve Anders Segerstedt (2004) “Inventory Control with a Modified Croston Procedure and Erlang Distribution”, International Journal of Production Economics, 90(3), s.361-367.
• Marsland, Simon (2009) Machine Learning: An Algorithmic Perspective, USA: A Chapman & Hall Book CRC.
• Mitchell, Tom M. (1997) Machine Learning, New York: MacGraw Hill.
• Nahmias, Steven (2013) Production & Operations Analysis, 6. Baskı, New York: McGraw Hill Education.
• Nikolopoulos, Konstantinos, Aris A. Syntetos, John E. Boylan, Fotios Petropoulos ve Vassilis Assimakopulos (2010) “An Aggregate-Disaggregate Intermittent Demand Approach (ADIDA) to Forecasting: An Empirical Proposition and Analysis”, Journal of the Operational Research Society, 62(3), s.544-554.
• Öztemel, Ercan (2012) Yapay Sinir Ağları, 3. Baskı, İstanbul:Papatya.
• Regattieri, Alberto, Mauro Gamberi, Rita Gamberini ve Riccardo Manzini (2005) “Managing Lumpy Demand for Aircraft Spare Parts”, Journal of Air Transport Management, 11(6), s.426-431.
• Syntetos, Aris A. ve John E. Boylan (2001) “On the Bias of Intermittent Demand Estimates”, International Journal of Production Economics, 71(1-3), s.457-466.
• Syntetos, Aris A. ve John E. Boylan (2005) “The Accuracy of Intermittent Demand Estimates”, International Journal of Forecasting, 21(2), s.303-314.
• Shenstone, Lydia ve Rob J. Hyndman (2005) “Stochastic Models Underlying Croston’s Method for Intermittent Demand Forecasting”, Journal of Forecasting, 24(6), s.389-402.
• Teunter, Ruud ve Babangida Sani (2009) “On the Bias of Croston’s Forecasting Method”, Journal of Operational Research, 194(1), s.177-183.
• Varghese, Vijith ve Manuel Rossetti (2008) “A Classification Approach for Selecting Forecasting Techniques for Intermittent Demand”, IIE Annual Conference Proceedings içinde, ABD: Institute of Industrial Engineers-Publisher, s.863.
• Wali, Akhil (2014) Clojure for Machine Learning, Birmingham: Packt.
• Wallström, Peter ve Anders Segerstedt (2010) “Evaluation of Forecasting Error Measurements and Techniques for Intermittent Demand”, International Journal of Production Economics, 128(2), s.625-636.
• Willemain, Thomas R., Charles N. Smart ve Henry F. Schwarz (2004) “A New Approach to Forecasting Intermittent Demand for Service Parts Inventories”, International Journal of Forecasting, 20(3), s.375-387.
• Willemain, Thomas R., Charles N. Smart, Joseph H. Shockor ve Philip A. DeSautels (1994) “Forecasting Intermittent Demand in Manufacturing: A Comparative Evaluation of Croston’s Method”, International Journal of Forecasting, 10(4), s.529-538.
• Yegnanarayana, Bayya (2005) Artificial Neural Network, Eastern Economy Edition, Yeni Delhi: Prentice-Hall of India.
• Zupan, Jure (1994) “Introduction to Artificial Neural Network Methods: What They Are and How to Use Them.”, Acta Chimica Slovenica, 41(3), s.327-352.