Intelligent Decision Support and Big Data for Logistics and Supply Chain Management

Permanent URI for this collection

https://hdl.handle.net/10125/63615

Browse

Recent Submissions

Now showing 1 - 5 of 5
  • Item
    The Drone-Assisted Traveling Salesman Problem with Robot Stations
    ( 2020-01-07) Schermer, Daniel ; Moeini, Mahdi ; Wendt, Oliver
    In this paper, we study the Drone-Assisted Traveling Salesman Problem with Robot Stations (TSP-D-RS). Specifically, we assume that there is a single truck that is equipped with a drone, and one or more potential sites of stations that might accommodate some robots. The TSP-D-RS asks for a valid route of the truck as well as feasible utilization of the drone and robots, such that all customers are served and minimal delivery time (makespan) or cost is accomplished. We provide a Mixed Integer Linear Programming formulation of the problem and perform a detailed numerical study. Through our numerical results, it is revealed that our formulation can be effectively addressed by a state-of-the-art solver. In addition, we demonstrate that optimizing the makespan coincides with reduced costs. In contrast, optimizing the operational costs might increase the makespan significantly. Furthermore, depending on the objective function, the operational utilization of the vehicles differs.
  • Item
    Evolving Neural Networks to Solve a Two-Stage Hybrid Flow Shop Scheduling Problem with Family Setup Times
    ( 2020-01-07) Lang, Sebastian ; Reggelin, Tobias ; Behrendt , Fabian ; Nahhas, Abdulrahman
    We present a novel strategy to solve a two-stage hybrid flow shop scheduling problem with family setup times. The problem is derived from an industrial case. Our strategy involves the application of NeuroEvolution of Augmenting Topologies - a genetic algorithm, which generates arbitrary neural networks being able to estimate job sequences. The algorithm is coupled with a discrete-event simulation model, which evaluates different network configurations and provides training signals. We compare the performance and computational efficiency of the proposed concept with other solution approaches. Our investigations indicate that NeuroEvolution of Augmenting Topologies can possibly compete with state-of-the-art approaches in terms of solution quality and outperform them in terms of computational efficiency.
  • Item
    Shortening Delivery Times by Predicting Customers' Online Purchases: a Case Study in the Fashion Industry
    ( 2020-01-07) Weingarten, Jennifer ; Spinler, Stefan
    Online retailers still struggle with the disadvantage of delivery times compared to traditional brick and mortar stores. With the emergence of big data analytics, it has become possible to extract meaningful knowledge from the volume of data that online retailers collect on their website. Nevertheless, limited research exists that investigates how this data can be used to optimize delivery times for customers. The goal of this paper is to develop a prediction model for anticipatory shipping, which predicts customers' online purchases with the aim of shipping products in advance, and subsequently minimize delivery times. Different forecasting methods in combination with k-means clustering are applied to test if, and how early, it is possible to predict online purchases. Results indicate that customer purchases are, to a certain extent, predictable, but anticipatory shipping comes at a high cost due to wrongly sent products. The proposed prediction model can easily be implemented and used to predict purchases, which can also be leveraged for other areas of application besides anticipatory shipping.
  • Item
    Novel Data Analytics Meets Conventional Container Shipping: Predicting Delays by Comparing Various Machine Learning Algorithms
    ( 2020-01-07) Viellechner, Adrian ; Spinler, Stefan
    Supply chain disruptions are expected to significantly increase over the next decades. In particular, delay of container vessels is likely to escalate due to rising congestion from continued growth of container shipping and higher frequency of extreme weather events. Predicting these delays could result in significant cost savings from optimizing operations. Both academic research and container shipping industry, however, lack analytical solutions to predict delay. To increase transparency on delay, we develop a prediction model based on 315 explanatory variables, 10 regression models, and 7 classification models. Using machine learning algorithms, we obtain best results for neural network and support vector machine with a prediction accuracy of 77 percent compared to only 59 percent of a naive baseline model. Various shipping players including sender, carrier, terminal operator, and receiver benefit from the easy-to-use prediction model to optimize operations such as buffers in schedules and the selection of ports and routes.
  • Item