Interaction of judgemental and statistical forecasting methods: issues &
Management Science
LATEX (2nd ed.): a document preparation system: user's guide and reference manual
LATEX (2nd ed.): a document preparation system: user's guide and reference manual
Bayesian forecasting and dynamic models (2nd ed.)
Bayesian forecasting and dynamic models (2nd ed.)
Time Series Analysis: Forecasting and Control
Time Series Analysis: Forecasting and Control
Web Database Applications with PHP & MySQL, 2nd Edition
Web Database Applications with PHP & MySQL, 2nd Edition
Web Design Flash Sites: Flash Sites (Icons)
Web Design Flash Sites: Flash Sites (Icons)
Computers and Operations Research
An Introduction to R
Forecasting product sales with dynamic linear mixture models
Forecasting product sales with dynamic linear mixture models
A model of the product lifecycle for sales forecasting
A model of the product lifecycle for sales forecasting
Web Standards Programmer's Reference: HTML, CSS, JavaScript, Perl, Python, and PHP
Web Standards Programmer's Reference: HTML, CSS, JavaScript, Perl, Python, and PHP
Production risk management system with demand probability distribution
Advanced Engineering Informatics
Hi-index | 0.00 |
An accurate short-term forecast of product sales is vital for the smooth operation of modern supply chains, especially when a company internationally outsources the manufacture of complex products. Sun Microsystems' business model has long emphasized such outsourcing. Historically, Sun has relied on a judgment-based forecasting process, involving its direct sales force, marketing management, and channel partners. However, management recognized the need to address the many heuristic and organizational distortions to which judgment-based forecasting procedures are prey. Simply replacing the judgmental forecasts by statistical methods with no judgmental input was unrealistic; short product life cycles and volatile demand confounded purely statistical approaches. This article documents a forecasting system that Sun developed and deploys currently; it uses Bayesian methods to combine both judgmental and statistical information. We discuss its development and architecture, including steps that Sun took to incorporate it into the existing forecasting and planning processes. We also present an evaluation of its forecasting performance and possible directions for future development.