Yunqiang Yin

Dujuan Wang

Huaxin Qiu

Sutong Wang

Qihang Xu

Yugang Yu

Joshua Ignatius

Problem definition: Promoting successful first-time delivery is the key to optimizing last-mile operational revenue, especially in the home appliance retail business for costly return shipping. This paper investigates how to identify and explain the potential delivery failure of each order at the last-mile hub under the promised delivery time, and accordingly regulate further distribution to realize a better outcome for its first-time delivery. Academic/practical relevance: Improving first-time attempts in last-mile deliveries is crucial to increasing customer satisfaction and retention as well as attracting new customers. To the best of our knowledge, this paper leads a data-driven research paradigm to predict the first-time delivery success of online orders. By targeting the orders which may likely fail to meet first-time deliveries, we can readjust order processing schedules at last-mile hubs to avoid delivery failures due to operational shortfalls. Methodology: We extend the multi-output interpretable classification model to forecast the delivery results by exploiting the complicated relationship between order status and relevant operational predictors. Considering the imbalanced data distribution in the success-failure prediction problem, we develop a two-stage cost-sensitive random forest chain (TCRFC) model to predict success rate and identify multiple outputs of potential delivery failures. This data-driven methodology reveals the importance of modeling the order flow process and integrating decision-making with predictive models in order delivery outcome forecasting. Results: After testing on the logistics operational-level dataset shared by RiRiShun Logistics (RRS), the proposed approach uncovers the key factors affecting the first-time delivery success rate, while demonstrating superior performance in predicting order delivery results. In addition, our work allows for better quality delivery decisions of order distribution processing based on real-time order prediction results. The simulation experiments estimate that the adjusted last-mile delivery plan can increase the success rate of the possible failed orders' first-time delivery by about 82.60% and save nearly $16,000 for return shipping compared to that of the original operations. Managerial implications: With effective predictions of order delivery outcomes at the last-mile hubs, logistics providers can make more targeted delivery commitments for the possible failed orders to increase successful first-time deliveries and promote customer loyalty. According to the identified type of potential failure, the operators may properly decide early or deferring delivery action of the corresponding order. And to further utilize resources for operational improvement to the best advantage, the operators can give priority to the orders which have key features with more significant impact on increasing the first-time delivery success rate.

Improving First-time Attempts in Last-Mile Deliveries

Yaochu Jin

This book provides an introduction to the models, methods, and results of some rescheduling problems in the presence of unexpected disruption events, including job unavailability, arrival of new jobs, and machine breakdown. The occurrence of these unexpected disruptions may cause a change in the planned schedule, which may render the originally feasible schedule infeasible. Rescheduling, which involves adjusting the original schedule to account for a disruption, is necessary in order to minimize the effects of the disruption on the performance of the system. This involves a trade-off between finding a cost-effective new schedule and avoiding excessive changes to the original schedule. This book views scheduling theory as practical theory, and it has made sure to emphasize the practical aspects of its topic coverage. Thus, this book considers some scenarios existing in most real-world environments, such as preventive machine maintenance, and deteriorating effect where the actual processing time of a job gets longer along with machine’s usage and age. To alleviate the effect of disruption events, some flexible strategies are adopted, including allocation extra resources to reduce job processing times or rejection the production of some jobs. For each considered scenario, depending on the model settings and on the disruption events, this book addresses the complexity, and the design of efficient exact or approximated algorithms. Especially when optimization methods and analytic tools fall short, this book stresses metaheuristics including improved elitist non-dominated sorting genetic algorithm and differential evolution algorithm. This book also provides extensive numerical studies to evaluate the performance of the proposed algorithms. The problem of rescheduling in the presence of unexpected disruption events is of great importance for the successful implementation of real-world scheduling systems. There is now an astounding body of knowledge in this field. This book is the first monograph on rescheduling. It aims at introducing the author's research achievements in rescheduling. It is written for researchers and Ph.D. students working in scheduling theory and other members of scientific community who are interested in recent scheduling models. Our goal is to enable the reader to know about some new achievements on this topic.

Models and Algorithms

Rescheduling Under Disruptions in Manufacturing Systems

T.C.E. Cheng

This book provides an introduction to the models, methods, and results of some due date-related scheduling problems in the field of multiagent scheduling. In multiagent scheduling, two or more agents share a common processing resource and each agent wants to optimize its own objective function with respect to its own set of jobs. Since the agents have conflicting objective functions, they have to negotiate among themselves with regard to sharing the common resource to optimize their own objective functions. A key feature of due date-related scheduling concerns the way in which due dates are considered: they can be given parameters or decision variables. For the former case, the motivation stems from the need to improve inventory and production management. For the latter case, due date assignment becomes a challenging issue since the decision-maker has to balance inventory holding costs against the benefits of fulfifilling orders in time. As for due dates, this book addresses the following three different scenarios: (i) The due dates of the jobs from either one or both of the two agents are decision variables, which are determined using some due date assignment models; (ii) The due dates of jobs in each job set are considered as given parameters, whereas which due date corresponds to a given job needs to determine; and (iii) The due date of each job is exogenously given. When the last case is involved, the objective function of each agent is related to the number of just-in-time jobs that are completed exactly on their due dates. For each considered scenario, depending on the model settings, and on the objective function of each agent, this book addresses the complexity, and the design of efficient exact or approximated algorithms. This book aims at introducing the author's research achievements in due date-related scheduling with two agents. It is written for researchers and Ph.D. students working in scheduling theory and other members of scientific community who are interested in recent scheduling models. Our goal is to enable the reader to know about some new achievements on this topic.

Due Date-Related Scheduling with Two Agents

Dujuan Wang

About

Books

Join the club