Delivery Cost Approximations for Dynamic Time Slot Pricing

In the past two decades, package home delivery has been a thriving business area. We focus on attended home delivery (AHD), for which it is necessary that the customer is at home during delivery. Many AHD companies offer their customers time slots for delivery, to provide high customer service and prevent costly delivery failures. We focus on dynamic pricing of time slots. To influence customers to choose a time slot that is cheaper for the company, i.e., time slots that represent less operational delivery time and travel distances, companies often give incentives (discounts) or penalties (delivery charges) dependent on the costs of a time slot. The main focus of this thesis is on determining the costs of a time slot and adjusting time slot pricing accordingly. Using machine learning models for predicting delivery costs we show that up to 6% more customers can be served and travel costs can be saved by 11% using dynamic pricing models.