Early Warning System Framework Proposal, Based on Big Data Environment

izvorni znanstveni rad

izvorni znanstveni rad

Early Warning System Framework Proposal, Based on Big Data Environment

Vrsta prilog u časopisu
Tip izvorni znanstveni rad
Godina 2019
Časopis International journal of artificial intelligence and machine learning
Nadređena publikacija International Journal of Artificial Intelligence and Machine Learning
Volumen 9
Svesčić 1
Stranice str. 35-66
ISSN 2642-1577
EISSN 2642-1585
Status objavljeno

Sažetak

Early warning systems are made with the purpose to efficiently recognize deviant and potentially dangerous trends related to company business as early as possible. The Big Data environment gives new opportunities and new approaches in analytical processes. There are numerous ways how to set up early warning systems within a company. The Big Data environment forces companies to apply new ways of thinking and use new disposable data sources. This article gives a novel concept for an early warning system design within a company, which is applicable in different industries. The core of the proposed framework is a hybrid fuzzy expert system which can contain a variety of data mining predictive models responsible for some specific areas as addition to traditional rule blocks. It can also include social network analysis metrics based on linguistic variables and incorporated within the rule blocks. As a part of this framework, SNA methods are also explained and introduced as powerful and unique tool to be used in modern early warning systems.

Ključne riječi

big data, data mining, social network analysis