File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ISSE51541.2021.9582469
- Scopus: eid_2-s2.0-85119090962
- WOS: WOS:000848245100006
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Delay Aware Dynamic Risk Assessment for Logistics Delivery
Title | Delay Aware Dynamic Risk Assessment for Logistics Delivery |
---|---|
Authors | |
Keywords | Delay Aware Risk Assessment Missing Data Analysis Smart Logistics Time Efficiency Estimation |
Issue Date | 2021 |
Citation | ISSE 2021 - 7th IEEE International Symposium on Systems Engineering, Proceedings, 2021 How to Cite? |
Abstract | On-time delivery is the most critical target of logistics industry that significantly impacts the efficiency of society and customer experience. Therefore, a wide variety of strategies have been employed for the operation of logistics systems to ensure the on-time rate. Despite these efforts, there could still be some delay in delivery induced by the factors such as the non-ideality of scheduling and extreme situations, which can potentially lead to severe consequences like economic losses. A potential approach to guarantee the time efficiency and prevent potential losses is to upgrade the processing priority of the packages with high delay risk. This motivates us to accurately recognize these packages and allocate the limited resources appropriately. A major challenge of this approach is that the risk needs to be assessed when the packages are being processed, in which scenario the information of the later steps is not known. In order to tackle that difficulty, this paper casts the risk assessment task into a classification problem, where the states of packages corresponding to the unfinished steps are treated as missing values. Subsequently, the optimization of the strategies for handling missing values is formulated using maximum likelihood estimation, which is solved simultaneously when training the model utilizing the decision tree structure. Finally, the proposed method is validated using real JD Logistics data. As demonstrated by the experimental results, the proposed method can accurately detect the packages with high delay risk even when they are still in early processing steps. Furthermore, our technique significantly outperforms a state-of-the-art method for classification with missing values. |
Persistent Identifier | http://hdl.handle.net/10722/336293 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Yuan | - |
dc.contributor.author | Hao, Shiqi | - |
dc.contributor.author | Liu, Yang | - |
dc.contributor.author | Hu, Shiyan | - |
dc.contributor.author | Zhe, Wenming | - |
dc.date.accessioned | 2024-01-15T08:25:16Z | - |
dc.date.available | 2024-01-15T08:25:16Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | ISSE 2021 - 7th IEEE International Symposium on Systems Engineering, Proceedings, 2021 | - |
dc.identifier.uri | http://hdl.handle.net/10722/336293 | - |
dc.description.abstract | On-time delivery is the most critical target of logistics industry that significantly impacts the efficiency of society and customer experience. Therefore, a wide variety of strategies have been employed for the operation of logistics systems to ensure the on-time rate. Despite these efforts, there could still be some delay in delivery induced by the factors such as the non-ideality of scheduling and extreme situations, which can potentially lead to severe consequences like economic losses. A potential approach to guarantee the time efficiency and prevent potential losses is to upgrade the processing priority of the packages with high delay risk. This motivates us to accurately recognize these packages and allocate the limited resources appropriately. A major challenge of this approach is that the risk needs to be assessed when the packages are being processed, in which scenario the information of the later steps is not known. In order to tackle that difficulty, this paper casts the risk assessment task into a classification problem, where the states of packages corresponding to the unfinished steps are treated as missing values. Subsequently, the optimization of the strategies for handling missing values is formulated using maximum likelihood estimation, which is solved simultaneously when training the model utilizing the decision tree structure. Finally, the proposed method is validated using real JD Logistics data. As demonstrated by the experimental results, the proposed method can accurately detect the packages with high delay risk even when they are still in early processing steps. Furthermore, our technique significantly outperforms a state-of-the-art method for classification with missing values. | - |
dc.language | eng | - |
dc.relation.ispartof | ISSE 2021 - 7th IEEE International Symposium on Systems Engineering, Proceedings | - |
dc.subject | Delay Aware Risk Assessment | - |
dc.subject | Missing Data Analysis | - |
dc.subject | Smart Logistics | - |
dc.subject | Time Efficiency Estimation | - |
dc.title | Delay Aware Dynamic Risk Assessment for Logistics Delivery | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ISSE51541.2021.9582469 | - |
dc.identifier.scopus | eid_2-s2.0-85119090962 | - |
dc.identifier.isi | WOS:000848245100006 | - |