PhD Defence: Clint Pennings
In his dissertation ‘Advancements in Demand Forecasting: Methods and Behavior’ ERIM’s Clint Pennings focuses on reducing or minimizing forecast errors in the retail industry.
Clint defended his dissertation in the Senate Hall at Erasmus University Rotterdam on Thursday, 10 November 2016 at 13:30. His supervisor was Leo Kroon, but to our deepest regrets he passed away on the 14th of September. Prof. Eric van Heck took over the role of supervisor. Clint’s co-supervisor was Dr Jan van Dalen. Other members of the Doctoral Committee were Prof. Ton de Kok (Technische Universiteit Eindhoven), Prof. Rene de Koster (Erasmus University), and Prof Aris Syntetos (Cardiff University)
About Clint Pennings
Clint Pennings (1986) has a bachelor's and master's degree from Utrecht University, and a master's degree from Erasmus University Rotterdam. In 2011, Clint started his PhD research at the Rotterdam School of Management as part of the Dutch Institute for Advanced Logistics (Dinalog) project 4C4More, a collaboration between several universities and companies. Within this project, he focused on extending available methods to generate more accurate forecasts and on modelling the behaviour of forecasters to analyse how the forecasting process can be improved. He is passionate about working with companies to apply statistics and machine learning in their business processes.
Clint presented his research at various international academic conferences, such as EURO, IFORS, and INFORMS, and at several more practice-oriented venues. Next to research he greatly enjoys teaching in the bachelor and master programmes. Currently, he works as a postdoctoral researcher at the Rotterdam School of Management.
Thesis Abstract
The demand that drives various activities in the supply chain is inherently uncertain, necessitating the need for forecasting. Retailers require forecasts for sales, inventory and order decisions, suppliers for production and procurement decisions, and distributors for capacity allocation decisions. In practice, forecast errors are substantial, which negatively affects operational performance. Reducing or minimizing these forecast errors is central to this thesis and is achieved by improving the forecasting capabilities of companies, which encompasses extending the available forecasting methods as well as analyzing how the forecasting process, the context in which these methods and models are embedded, can be improved.
Photos: Chris Gorzeman / Capital Images
