Special Interest Group on Supply Chain Forecasting
The Lancaster Centre for Foreasting hosts a number of different research interests, past and current research grants, applied research projects with companies and PhD students in the area of Forecasting for Supply Chain Management.
Collaborative forecasting research study
The increased volatility and competitiveness of today’s market has led firms to engage in collaborative forecasting and information-sharing practices in order to improve forecast accuracy. However, knowing how and when to collaborate with downstream partners remains a challenge. It seems that the benefits are widely touted though little substantive research exists about how to best use the mass of downstream data available to forecast more accurately.
At the Lancaster Centre for Forecasting we are conducting a research study to address some of the open questions in this domain, initially through a web-based survey of forecasters and demand planners. The survey can be found at www.collaborative-forecasting.co.uk/survey/cf_survey.html and your participation is encouraged. To be more specific, we are focusing on the following research questions:
- What forms of collaboration are companies participating in and what data is being shared by their downstream partners?
- How are firms using this information, if at all, in their forecasting process? Through statistical methods, analytics or judgement?
- How do firms cope with differing data conditions and forecasting requirements of different customers?
Our theory is that there is a huge amount of data available, but except for a few idealistic cases published, companies are either not able to leverage the data through their forecasting systems and rely on either a judgemental or exception management approach rather than the advanced statistical techniques available. In a later phase, we look to test alternative methods of integrating downstream data into the statistical forecasting process automatically and compare accuracy with established benchmark methods.
If you have any further questions or wish to show an interest in participating in the study, please do not hesitate to email matt.weller@lancaster.ac.uk.
Supply Chain Forecasting - Practitioner Round Table
The Forecasting round table, initiated and run mutually with Jonathan Aylen and Kevin Albertson through Manchester University, provides a free and open forum for pratitioners, demand planners, forecasting and supply chain managers from retail, manufacturing and suppliers of consumer packaged goods (both durable and non-durable). In addition, it facilitates an open exchange with software vendors and academics with an interrest in forecasting for supply chain management.
Successful first meeting of the Supply Chain Forecasting Round table
Thursday 14th October 2010, City University, London, UK
The Lancaster Centre for Forcasting is pleased to have run the first successful half-day event in a series workshops uniting practitioners, academics and vendores in Supply Chain forecasting, funded by and in collaboration with the British OR Society on
"Forecasting with Promotions - Current Practice and future prospects"
This afternoon event covered different aspects of the challenges in promotional forecasting & evaluation for supply chain management, which badly affects retailers and manufacturers alike. The two keynote presenters, Gareth Brentall (MD of Promax Europe Ltd) and Barry Grange (CEO of Retail Express), both with many years of practical experience in the area, described their own distinctive approaches to the challenges in promotional forecasting. The event kicked off with Prof. Robert Fildes, director of the Lancaster Centre for Forecasting, with an overview of current practices and research in promotional forecasting. The event offered ample opportunity to network amongst practitioners, vendors and academics, and included three keynote talks:
Current research in Forecasting Promotions - Judgment v Statistics?
Prof. Robert Fildes, Distinguished Professor, Lancaster Centre for Forecasting
Promotional Forecasting
Barry Grange, CEO of Retail Express
What's a good Promotion?
Gareth Brentall, MD Promax Europe Ltd.
Please find the event Agenda (pdf ) on Forecasting with Promotions to download or print the full announcement, including times, abstracts of the talks, speaker biographies, address and directions. The full details including the presentations and corresponding reports can be found on the Forecasting Event announcement.
Attendance at this and future events is FREE but places are limited, so you must register by email. To receive future invitations - please email Sven Crone at s.crone@lancaster.ac.uk.
Please click on the link below to find the full announcement including abstracts , biographies, and directions to the event on Forecasting with Promotions in London.
Forecasting using Statistical Models Combined with Judgment
Supply chain planning is wholly reliant on accurate forecasts in most industries and these forecasts are provided through FSSs. Current evidence suggests that these systems are not used effectively so that large and costly errors are associated with the resulting forecasts. This is a continuing project examining all aspects of supply chain forecasting. Such forecasts are made using a base-line statistical method which is then adjusted by expert company forecasters to deliver a 'final' forecast. This final forecast is then used in all aspects of supply chain planning affecting service levels, cash flow, human resource scheduling etc.
Initially, the UK based Engineering and Physical Sciences Research Council (EPSRC) funded a research project in Forecasting Support Systems. The project, over three years, was supervised by Professor Robert Fildes (Lancaster University Management School) and Professor Paul Goodwin (School of Management, University of Bath) with Dr Konstantinos Nikolopoulos acting as Research Officer (Please visit Project web site). It had as its focus two issues:
- the inefficient use of managerial judgment when adjusting the statistical forecasts to take into account special events such as promotions.
- the design of forecasting support systems to improve judgments.
The research has continued through the appointment of doctoral researchers and a Marie Curie Fellow, Dr Juan Trapero Arenas. He examined non-linear effects when experts respond to information (please see his project report). The initial findings are published in the Journal of Forecasting.
Within the supply chain an important phenomenon undermining efficient supply chain performance is the bullwhip effect. This occurs when demand uncertainty at the retailer is amplified for the manufacturer. The phehomenon arises due to retailer ordering patterns and lead time delays. Juan, working with Dr Nikos Kourentzes and Professor Robert Fildes has examined how information sharing between retailer and manufacturer can help improve forecasting performance and overcome the adverse effects of the bullwhip, presented in a working paper..
Research students & topics in the Supply Chain forecasting group:
Dr. Stavros Asimakopoulos - Thesis: A human-computer interaction perspective on forecasting systems design
Andrey Davydenko - Thesis. Integration of judgmental and statistical approaches for demand forecasting: models and methods
Ioannis Stamatopoulos - Thesis: The impact of demand uncertainty on supply chain perfomance and the value of collaboration
Dr Juan Trapero Arenas - Marie Curie Fellowship: Supply Chain demand forecasting based on unobserved component models. His final report of his fellowship is in the attached document.
Matt Weller - Thesis. Forecasting models for supply chain collaboration. The research aims to investigate the information exchanged between retailers and manufacturers and how it is used in the forecasting process. Collaboration between partners (as well as internally through S&OP) is growing and with it comes a large volume of data which can be leveraged to drive forecast improvement.
For all enquiries please contact Dr. Sven F. Crone, deputy director of the forecasting centre at s.crone@lancaster.ac.uk
