Improved supply chain management based on hybrid demand forecasts

Demand forecasts play a crucial role for supply chain management. The future demand for a certain product is the basis for the respective replenishment systems. Several forecasting techniques have been developed, each one with its particular advantages and disadvantages compared to other approaches. This motivates the development of hybrid systems combining different techniques and their respective strengths. In this paper, we present a hybrid intelligent system combining Autoregressive Integrated Moving Average (ARIMA) models and neural networks for demand forecasting. We show improvements in forecasting accuracy and propose a replenishment system for a Chilean supermarket, which leads simultaneously to fewer sales failures and lower inventory levels than the previous solution.

[1]  Eric Wan,et al.  Finite Impulse Response Neural Networks for Autoregressive Time Series Prediction , 1993 .

[2]  Chris Chatfield,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[3]  William Remus,et al.  Neural Network Models for Time Series Forecasts , 1996 .

[4]  Petra Perner,et al.  Data Mining - Concepts and Techniques , 2002, Künstliche Intell..

[5]  Elizabeth Bradley.  Analysis of time series , 2003 .

[6]  C C Reyes-Aldasoro,et al.  A hybrid model based on dynamic programming, neural networks, and surrogate value for inventory optimisation applications , 1999, J. Oper. Res. Soc..

[7]  Kenneth Gilbert,et al.  An ARIMA Supply Chain Model , 2005, Manag. Sci..

[8]  Amar Gupta,et al.  Brief Application Description. Neural Networks Based Forecasting Techniques for Inventory Control Applications , 1998, Data Mining and Knowledge Discovery.

[9]  S. Kantamneni,et al.  POS and EDI in retailing: an examination of underlying benefits and barriers , 2002 .

[10]  J. Faraway,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[11]  Richard Weber,et al.  Demand Forecast in a Supermarket Using a Hybrid Intelligent System , 2003, HIS.

[12]  Peter C. McCluskey,et al.  Feedforward and Recurrent Neural Networks and Genetic Programs for Stock and Time Series Forecasting , 1993 .

[13]  Oliver Vornberger,et al.  Sales forecasting using neural networks , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[14]  Ajith Abraham,et al.  A neuro-fuzzy approach for modelling electricity demand in Victoria , 2001, Appl. Soft Comput..

[15]  Georg Dorffner,et al.  Neural Networks for Time Series Processing , 1996 .

[16]  D. Lambert,et al.  Fundamentals of Logistics Management , 1998 .

[17]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[18]  Steven C. Wheelwright,et al.  Forecasting methods and applications. , 1979 .

[19]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[20]  William Remus,et al.  Neural Networks for Time-Series Forecasting , 2001 .

[21]  David J. Hand,et al.  Intelligent Data Analysis: An Introduction , 2005 .

[22]  Chin Kuo,et al.  Neural Networks vs. Conventional Methods of Forecasting , 1996 .

[23]  John Moody,et al.  Prediction Risk and Architecture Selection for Neural Networks , 1994 .

[24]  Teck-Hua Ho,et al.  An Empirical Analysis of Forecast Sharing in the Semiconductor Equipment Supply Chain , 2005 .