In attended home delivery services, the time slot offering problem is of high importance, as it significantly impacts the retailer’s efficiency in providing this service. Customer choice behavior is a crucial factor to be considered in this planning problem. To facilitate this task, customer choice models have been developed that reflect the customer decision-making process. A particularly realistic choice model is the consider-then-choose model. This non-parametric customer choice model consists of two steps: in a first step, all eligible time slots are
identified and in a second step, the considered time slots are ranked and the highest-ranked time slot is chosen. In this study, we use the consider-then-choose model to solve the time slot assortment problem.
We propose an approach to estimate this choice model from historical transaction data and incorporate a structure that can be exploited in the online time slot offering decision. We evaluate our estimation and optimization approach in a realistic numerical study.
Dieser Eintrag ist Teil der Universitätsbibliographie.
Search Authors in
