Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: analiza Big Data

Sortuj według:

Ogranicz wyniki do:

Intelligent analysis of import and export in green trade barrier based on big data analysis

Mao Yu, Lu Shan

Ecological Chemistry and Engineering. S

2024

Vol. 31, nr 1

117--126

With the rapid development of economic globalisation, global economic and trade activities are escalating. However, environmental problems and the emergence of green economy, a response to these problems, has led to the widespread introduction of green trade barriers. These barriers implicitly limit the development of trade activities. This paper focuses on the export difficulties caused by green trade barriers and proposes a method to quantify discrete product characteristics, explore the internal characteristics of commodities and decide optimally on intended export regions. Firstly, the discrete feature of products is quantified by quantitative transformation method. Secondly, the quantitative data are used to derive the best decision for export regions through support vector regression (SVR) method. Particle swarm optimisation is used in optimising SVR parameters to achieve high-precision decision making. Comparison with historical data from the industry park shows the identification accuracy of the optimised SVR model to be better than that of the traditional regression model. This finding presents a novel perspective for developing import and export under the background of green trade barriers.

Use of big data analysis to identify possible sources of supply chain disruption through the DOTMLPFI method

Nagy Judit, Foltin Pavel, Ondryhal Vojtech

LogForum

2022

Vol. 18, no. 3

309--319

Backgrounds: The presented research deals with the investigation of how big data analytics can help predict possible disruptive events in supply chains. The supply chain can be considered a complex system with a wide spectrum of possible sources of internal and external disruptions. Since the individual entities of the supply chains operate in a particular environment and interact with this environment, there is a certain level of mutual interdependency. This set of interconnected interactions within the supply chain will be the unit of analysis. Methods: There are many internal and external sources of supply chain disruption, which opens up the potential application of Big Data Analysis (BDA) as an early warning tool. To analyse the possible application of the BDA to identify sources of supply chain disruptions, we conduct a bibliometric analysis to define an appropriate structure for supply chain risk classification as well as appropriate keywords that make data collection quicker and easier. The DOTMLPFI methodology was used to systematically identify the most relevant risks threatening the supply chains. Results: The proposed research approach creates a possible framework to support the operational sustainability and resilience of the supply chain as a system, toward internal and external disruptions. The research results also point out the most explored attributes of supply chain disruption. The conducted bibliometric research and content analysis support the theoretical framework of using BDA as a possible early warning tool, especially for the identification of possible sources of supply chain disruption. The approach of grouping Big Data sources into categories based on DOTMLPFI groups allows to identify the appropriate keywords for their later BDA analysis. The analytical framework provides a starting point for individual supply chain entities to understand risks and systematically collect the appropriate data in the required structure about them. Conclusion: The complexity of supply chains, together with the increasing possibility of digital applications, requires a new analytical framework for evaluating the overall supply chain, with the possible application of new data sources and analytical approaches regarding the risks threatening the chain. DOTMLPFI methodology allows covering all the relevant categories of supply chain risks, and by proposing relevant keywords and data sources it can help companies to find the appropriate open-source, up-to-date information and be prepared for disruptive events.