FORESIGHT, Issue 44

Description

Winter 2017

Special Feature: A New Forecasting Paradigm: Play Defense

Changing the Paradigm for Business Forecasting by Michael Gilliland
“It’s been over 50 years since the physicist/ philosopher Thomas S. Kuhn published his important and influential book, The Structure of Scientific Revolutions. For me, as a philosophy and math student in the 1970s, Kuhn’s book was required reading. But the book’s argument about the nature of the progression of scientific knowledge has had influence well beyond its original intended audience. And I think it can be applied to business forecasting today.”

Commentary by David Orrell
Michael Gilliland argues convincingly that we need a paradigm shift in forecasting, away from an “offensive” approach that is characterized by a reliance on complicated models and towards a more “defensive” approach which uses simple but robust models. While I agree completely with his conclusion that simple models are usually preferable to complicated models, I would add that the problem is less an obsession with complexity per se, than with building detailed mechanistic models of complexity.

Articles

1. Recoupling the Forecasting and Stock-Control Processes by Steve Morlidge and Aris Syntetos
   The integration of demand forecasting and inventory control is an area that deserves increased attention from practitioners as well as more research work from academics. In inventory planning, there is an explicit linkage between the variance of the forecast errors over the replenishment lead time and the calculation of safety stocks. If the calculation of the forecast error variance is flawed, then the calculation of the safety stocks will be flawed too. The implications can be dramatic: if stocks are too high, there is a financial penalty. If they are too low, service levels will be compromised.
2. Research into Forecasting Practice by Robert Fildes
   Continuing our discussions in recent issues of the need for better connections between academic research in forecasting and business needs and practices, Robert Fildes, a founder of the International Institute of Forecasters in 1980 and founding director of the Lancaster Centre for Forecasting in the UK, has taken a close look at the publications in forecasting journals, finding a troubling deficiency of research for improving supply chain management. The fix isn’t easy and requires much better collaboration among researchers, businesses, and software vendors.
3. Collaborative Forecasting: Is It Always Worth It? by Paul Goodwin
   Common sense suggests that there will be gains in forecast accuracy if organizations at different points in a supply chain collaborate by sharing information about plans, orders, and current inventory levels. Reduced forecasting errors should, in turn, lead to less cash tied up in inventories, higher order fill rates, shorter replenishment frequencies, greater availability of products, and improved customer service.
4. Book Review by Stephanie Globus and Aris Syntetos
   Demand Forecasting for Managers by Stephan Kolassa and Enno Siemsen