A multi-stage data mining approach for liquid bulk cargo volume analysis based on bill of lading data

Suhyeon Kim,Wonho Sohn,Dongcheol Lim,Junghye Lee

doi:10.1016/j.eswa.2021.115304

Suhyeon Kim, Wonho Sohn + Show 2 more

Open Access

https://doi.org/10.1016/j.eswa.2021.115304

Copy DOI

Abstract

Liquid bulk cargo (LBC) volume analysis has received considerably great attention recently since LBC is a valuable and high-demand cargo. Thus, it is important to establish an analysis system for LBC volume, as it can help inform strategies for port planning and management. Nevertheless, LBC volume analysis is a challenging task for researchers because trends in LBC volume are highly volatile and non-stationary. In this paper, a new framework for enabling informative LBC volume analysis based on bill of lading (BL) data is proposed, which consists of three parts: item segmentation, exploratory volume analysis, and volume prediction. Firstly, an innovative item segmentation system using item texts of BL data was developed, which can generate subcategory as well as category information of LBC items that existing system cannot provide. Next, exploratory volume analysis was performed to understand the volume characteristics of each categorized and subcategorized item in terms of geography and timeline. Lastly, manifold learning- and deep learning-based time series techniques were proposed to increase LBC volume prediction accuracy compared with existing statistical models. The experimental results for volume prediction show the accuracy increased by 34% and 18% in average at category and subcategory levels over baseline models. It is believed that our proposed method will be helpful for stakeholders in maritime logistics, giving them the insights that they need to make better decisions.

Highlights

Maritime logistics is one of the most important sectors in global trade and supply chain networks (Fagerholt et al, 2017; Zhou et al, 2019)
96% of the 15,249 item texts was classified into the correct categories and subcategories by using the Liquid bulk cargo (LBC)-ID and the LBC-specific spell checker (LBC-SC) (q ≥ 10)
An actual example of item segmentation results can be found in Table 5, comparing the item seg mentation results of the ITS with the HS code-based item segmentation system (HSCS)

Summary

Introduction

Maritime logistics is one of the most important sectors in global trade and supply chain networks (Fagerholt et al, 2017; Zhou et al, 2019). In port cargo volume analysis, data for customs and data for a port community system (PCS) (here onwards, customs data and PCS data respectively) are used worldwide in the maritime industry (Adland et al, 2017; Guszczak & Mencarelli, 2020) Both data generally provide port cargo volume statistics aggregated based on bill of lading (BL) data, a detailed receipt of a shipment of goods and the standard for cargo import–export declaration in ports. For LBC exploratory volume analysis, most of the studies are mainly focused on identifying the po tential sources (cargoes or regions) for LBC trade or building the plans and strategies related to the operation of ports for LBCs by ana lyzing the statistics of LBC volume. Petersburg and Amderma lying along the Northern Sea Route (NSR) based on several exploratory data analyses in terms of timeline and geographical views; the purpose of their study is to build port planning by considering situation and future demand for the ports related to the NSR

Results

Discussion

Conclusion