Research Agenda


1. Information sharing in supply chains (value of advance demand information)
In this line of research, we study the impact of early information about uncertain customer demand in a supply chain. Information about future demand, such as better forecasts or reservations from customers, improves decision making in most operations settings, through better planning and reservation of capacity for priority customers.

We study the value of advance demand information in three different types of supply chains:

(a)    Agri-Food industry: For the seed supply chain, we show that obtaining early information on demand has a significant impact on profitability, because it helps the decision makers to better allocate limited supply to the most profitable markets. We derive simple rules where demand information has the largest impact and what the overall value of this information is. In addition, we derive easy-to-use decision support tools that help the supplier in making its allocation decisions. We employ stochastic dynamic programming for this research (link to the working paper)

 

(b)   Logistics industry: In fleet management, we show how to make use of early information such as reservations from customers to improve fleet management. We provide methods to support decision making and demonstrate that using reservation information has a strong impact on overall profitability of a transportation service provider. We use Markov chain modeling and the Theory of Markov Decision Processes for this research (link to research publication, link to earlier pre-publication working paper)

 

(c)    Chemical / consumer goods industry: We analyze a supply chain in which a demand planner provides demand forecasts to a production planner. The production planner uses the forecast to decide on the production quantity and consequently needs information about the accuracy of the forecast. The production planner cannot observe the effort that the demand planner invests and has to follow his belief about the demand planner’s effort level. If the true effort of the demand planner and the belief of the production planner are not aligned, the overall performance of the supply chain suffers. Such a setting can be observed in a variety of industries, including the consumer electronics industry and the chemical industry. We develop a game theoretic model to show that social preferences affect the alignment between demand planner and production planner. Using laboratory experiments we find support for the theoretical results: Some demand planners invest effort, and production planners correctly anticipate this effort. We show that group identity can be used as a mean to increase social preferences and to incentivize the demand planners to invest more effort and help the production planners to anticipate forecast accuracy more accurately. Our results reveal that supply chains can work effectively even if the behavior of some actors is difficult to observe and that the creation of group identity is an approach to improving forecasts, which supplements existing approaches such as monetary incentives. We employ behavioral experiments for this research (link to the working paper)
 
 
2. Energy management in manufacturing and operations
In this line of research, we develop control methods and algorithms that support energy management systems in manufacturing processes, buildings, and operations. For example, production facilities use energy management software and tools to manage the overall energy consumption of their processes. Energy management tools and new electric motor technologies are expected to be a major lever in the struggle to reduce global CO2 emissions (see e.g. the report Capturing Opportunities in Energy Efficiency of the World Economic Forum 2011). Variable speed drives and energy management tools allow companies to control the speed and the status of each production step and to have a real-time overview on energy consumption. The production manager can slow down or halt whole production steps or lines to balance the overall consumption level. While this can significantly reduce energy costs as well as carbon emissions, it has an impact on the overall performance of the operations process. We evaluate this impact of energy management on production performance and we develop planning methods that take into account energy consumption.
 

3. Capacity planning of vehicle fleets
Transportation logistics providers today invest heavily into fleets of transportation vehicles such as rail cars, rental cars, or containers. The size of such fleets can amount to several hundreds of thousands of vehicles and maintaining such fleets requires investments of up to several billions of Euros.

Planning the size and structure of a vehicle fleet is therefore a crucial but complex decision. Too small fleets or fleets with the wrong vehicle types can significantly compromise the service level of the fleet and cause losses in sales and customer goodwill. Too large fleets lead to low utilization and consequently high fleet operating and capital holding costs.

First, we investigate the problem of determining suitable fleet capability, given the above trade-off between operating costs and service requirements. We consider additional factors such as uncertainty about demand forecasts, seasonal demand variations, the composition of the fleet, and specific service level requirements. We develop insights and easy-to-use quantitative planning models to support decision making (link to publication, link to pre-publication working paper).

Second, we support logistics providers by improving their revenues through differentiating between different types of customers. Today, different customers have different service requirements. While customers from industries such as automotive or high tech require reliable transportation service to maintain their just-in-time supply chains, other customers are looking for transportation service at competitive prices but with less requirements on availability. We show how logistics providers can adapt their fleet management to take advantage of these differences (link to publication).

For this line of research, we use stochastic modeling, queuing theory, and Markov chain analysis. We work together with a leading European rail car transportation provider.


4. Tailored operations and supply chain research
Together with researchers from leading institutions, I provide tailored research upon request. We can draw on considerable experience in supply chain management, inventory planning, capacity management, spare parts planning, and computer simulation. If you are interested in discussing open questions in the operations of your company, feel free to contact me
Comments