Big data predictions of Seasonal Fluctuations in Marine Traffic (using AIS data) by monitoring idle ships
The current article analyzes big data and makes predictions for the sea freight transport trends. It aims to support the management of sea transport, improve sea logistics services to predict trends in sea freight transport, support the management of sea transport, improve sea logistics services, a...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Economics – Varna
2024-12-01
|
| Series: | Business & Management Compass |
| Subjects: | |
| Online Access: | https://bi.ue-varna.bg/ojs/index.php/bmc/article/view/83 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The current article analyzes big data and makes predictions for the sea freight transport trends. It aims to support the management of sea transport, improve sea logistics services to predict trends in sea freight transport, support the management of sea transport, improve sea logistics services, and optimize the organization of transport services. The used data are data from the Automatic identification system (AIS data). The methods used are SQL queries and Excel functions for data extraction and calculations for data to receive results about seasonality and structural change indexes in five years (2019-2023). The study examines seasonality and idle ship indexes for the most commonly used ship types carrying cargo divided into three categories: cargo, tanker, and other types of ships. The results of calculations indicate a pronounced seasonality in the number of idle ships transiting through the Port of Varna, which appears to be directly proportional to the "idle ship" metric. Specifically, a decline in the idle ship index correlates with a decrease in the overall number of vessels. This relationship leads to an important inference: no unnecessary delays occur at the Port of Varna. Instead, any significant delays observed are primarily attributed to an increased number of ships during certain months. By understanding the cyclical patterns and supply-demand dynamics in the sea freight market, logistics providers can make more informed decisions and adapt their strategies accordingly. For the research period, other similar research is absent in the field of big data analysis in maritime traffic.
|
|---|---|
| ISSN: | 3033-0106 |