Forecasting Supply Chain Demand Using Machine Learning Algorithms - Distributed Artificial Intelligence, Agent Technology, and Collaborative Applications - page 359

One important point to note is that support vector machines are computationally intensive and the
cross-validation-based complexity parameter optimization procedure results in running a large amount
of support vector machines depending on the precision of the complexity search. The longest running
models in this research took over 3 days of processing on a modern computer. There are many optimiza-
tion techniques that could be performed to reduce the processing time such as parallelization, which is
trivial for a cross-validation procedure and reduction of the complexity term search precision. We hope
that in time, further optimizations to the support vector machine algorithms and an increase in process-
ing power would reduce the processing time significantly. Once the models have been completed, they
can be used for forecasting with relatively little processing time. There is also research into hardware
based support vector machine implementations. One such initiative is the Kerneltron project, which
provides performance increases by a factor of 100 to 10,000 (Genov & Cauwenberghs, 2001, 2003;
Genov, Chakrabartty, & Cauwenberghs, 2003), thus increasing the probability that such large SVM
applications are feasible in the medium term future.
One important possibility for future research would be investigating the benefits of the ML techniques
when using other sources of data and in the context of collaborative forecasting. This additional data
may include economic indicators, market indicators, collaborative information sources, product group
averages and other relevant information.
r eferences
Anonymous. (2005). Inventory carrying costs. The Controller's Report , (4), 5.
Assimakopoulos, V., & Nikolpoulos, K. (2000). The theta model: A decomposition approach to forecast-
ing. International Journal of Forecasting, 16 (4), 521.
Box, G., Jenkins, G. M., & Reinsel, G. (1994). Time series analysis: Forecasting and control (Third
ed.). Englewood Cliffs: NJ: Prentice Hall.
Chandra, C., & Grabis, J. (2005). Application of multi-steps forecasting for restraining the bullwhip
effect and improving inventory performance under autoregressive demand. European Journal of Op-
erational Research, 166 (2), 337.
Cox, A., Sanderson, J., & Watson, G. (2001). Supply chains and power regimes: Toward an analytic
framework for managing extended networks of buyer and supplier relationships. Journal of Supply
Chain Management, 37 (2), 28.
Davis, E. W., & Spekman, R. E. (2004). The extended enterprise: gaining competitive advantage through
collaborative supply chains. Upper Saddle River: NJ: FT Prentice Hall.
de Figueiredo, R. J. P. (1980). Implications and applications of Kolmogorov's superposition theorem.
IEEE Transactions on Automatic Control, 25 (6), 1227-1231.
Dejonckheere, J., Disney, S. M., Lambrecht, M. R., & Towill, D. R. (2003). Measuring and avoiding
the bullwhip effect: A control theoretic approach. European Journal of Operational Research, 147 (3),
567.