Robert Fildes (presenting author), Distinguished Professor (Emeritus) and Founding Director, Centre for Marketing Analytics and Forecasting, Lancaster University Management School, UK
Paul Goodwin, Professor Emeritus, School of Management, University of Bath; UK
February 9th 2023
12 PM to 12.40 PM (UK GMT-1)
1 PM; to 1.40 PM (CET, Berlin)
https://us02web.zoom.us/j/89160497274?pwd=TkRkMDAvaGpIMVNXLzhWWmc5UVRUUT09
Meeting-ID: 891 6049 7274
Kenncode: 857585
Comment: In case of technical problems, please visit https://www.euro-online.org/websites/bor/behavioral-operation-research-brown-bag-seminar-series/ before the start of the meeting.
Abstract:
Most private and many public organizations employ ‘demand planners’ whose job it is to forecast the sales (or activities) arising in their organization. The processes, which the planners undertake, are usually complex, often involving interactions with many colleagues, information from external sources, and ‘advice’ from forecasting software. In this presentation, we describe a typical demand planning process, highlighting the information used and misused through the lens of the ‘heuristics and biases’ literature. Research in this area, based on both experiments and field studies, has been limited. In the current study, we integrate 6 data sources to highlight commonalities in the process by which a final demand forecast is reached. The conclusions are striking and underline the importance of a forecasting system that limits the damage arising from the biases of the participants.
Why should you join?
Demand forecasting is ubiquitous. Understanding the processes by which information is interpreted in order to produce a final forecast, which is then used in various operational decisions, is important in practice – poor forecasting has serious financial consequences. But it is also of great current theoretical interest as it asks and partially answers the question of how users interpret the information arising from increasingly complex AI type models. Methodologically, successful research requires a ‘mixed method’ approach.