| Autor: |
Laxman D. Netak, Arvind W. Kiwelekar, Akshay Ghodake, Prasad C. Mahajan |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
Lecture Notes in Electrical Engineering ISBN: 9789811636899 |
| DOI: |
10.1007/978-981-16-3690-5_30 |
| Popis: |
Handling uncertainty in information is one of the biggest challenges faced by logistics management and freight forwarding agencies. The uncertainty may be in user needs, availability of raw materials, Estimated Time of Arrivals (ETA) of shipments, or occurrence of any natural calamities. These agencies are increasingly adopting intelligent ways of handling uncertainties in the information. In this paper, we describe a machine learning-based approach to deal with the uncertainty in the Estimated Time of Arrivals (ETA) of shipments. The approach uses multiple regression techniques to predict the ETA of a shipment at the destination port. The approach uses data from two different sources. First is the in-house internal data about shipments maintained by a company. Second is the marine traffic data collected through the Automatic Identification System (AIS). The approach combines these two data to predict the ETA of a shipment. The approach predicts the ETA of the shipment with 89% accuracy. The prediction model described in the paper is being in use and the predicted ETA has been found helpful to effectively manage resources in the downstream supply chain such as human sources at port, transporter and customers inquiries. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
