WHY DO COMPANIES NOT PRODUCE BETTER FORECASTS OVERTIME? AN ORGANISATIONAL LEARNING APPROACH

Abstract This paper considers the forecasting practice of a U.K. branch of a major international pharmaceutical company. The company uses a Forecasting Support System to prepare system forecasts, which are later ‘judgmentally’ adjusted to produce a set of final forecasts. Although it is anticipated that as the company gains experience and becomes familiar with its product, its ability to forecast at the stock keeping unit level will improve, an analysis of forecasts for 136 products over a 24-month period shows that this is not the case. This present study speculates as to the possible reasons behind what is ostensibly a failure to learn and draws on key concepts from organisational learning in an attempt to explain what may be happening.

[1]  Michael Lawrence.  The M2-competition: Some personal views , 1993 .

[2]  P. Goodwin,et al.  On the asymmetry of the symmetric MAPE , 1999 .

[3]  Paul Goodwin,et al.  Integrating management judgment and statistical methods to improve short-term forecasts , 2002 .

[4]  Liam Fahey,et al.  The Eleven Deadliest Sins of Knowledge Management , 1998 .

[5]  Robert Fildes,et al.  Judgmental forecasts of time series affected by special events: does providing a statistical forecast improve accuracy? , 1999 .

[6]  Marcus O'Connor,et al.  Sales forecasting updates: how good are they in practice? , 2000 .

[7]  Moira Watson,et al.  Forecasting in the Scottish electronics industry , 1996 .

[8]  John T. Mentzer,et al.  Conducting a sales forecasting audit , 2003 .

[9]  Brian P. Mathews,et al.  Judgemental revision of sales forecasts: Effectiveness of forecast selection , 1990 .

[10]  A. Diamantopoulos,et al.  Judgemental revision of sales forecasts: A longitudinal eetension , 1989 .

[11]  Robert Fildes,et al.  Forecasting Systems for Production and Inventory Control , 1992 .

[12]  C. Chatfield,et al.  The M2-competition: A real-time judgmentally based forecasting study , 1993 .

[13]  Adamantios Diamantopoulos,et al.  Judgemental revision of sales forecasts: The relative performance of judgementally revised versus non‐revised forecasts , 1992 .

[14]  Robert Fildes,et al.  The design features of forecasting support systems and their effectiveness , 2006, Decis. Support Syst..

[15]  Spyros Makridakis,et al.  The M3-Competition: results, conclusions and implications , 2000 .

[16]  David Reilly,et al.  Personal views of the M2-competition , 1993 .

[17]  P. Goodwin.  Improving the voluntary integration of statistical forecasts and judgment , 2000 .

[18]  Robert D. Klassen,et al.  Forecasting practices of Canadian firms: Survey results and comparisons , 2001 .

[19]  Paul Goodwin,et al.  Heuristics, biases and improvement strategies in judgmental time series forecasting , 1994 .

[20]  Terence C. Mills.  The M2-competition: Some personal reflections , 1993 .

[21]  E. S. Gardner,et al.  Forecasting Trends in Time Series , 1985 .

[22]  Chris Chatfield.  A personal view of the M2-competition , 1993 .

[23]  Robert L. Winkler,et al.  The accuracy of extrapolation (time series) methods: Results of a forecasting competition , 1982 .

[24]  Michael Lawrence,et al.  A field study of sales forecasting accuracy and processes , 2000, Eur. J. Oper. Res..