Special Issue on Graph-based Methods for Large Scale Financial and Business Data Analysis
摘要截稿:
全文截稿: 2020-06-30
影响因子: 7.196
期刊难度:
CCF分类: B类
中科院JCR分区:
• 大类 : 计算机科学 - 1区
• 小类 : 计算机:人工智能 - 1区
• 小类 : 工程:电子与电气 - 1区
Overview
Machine learning and pattern recognition techniques have had a significant impact on the analysis of large-scale datasets in the financial domain. However, to date most of the analysis techniques used have focused on the use of standard vectorial methods and time series data. Recently though, interest has turned to the use of relational and similarity-based representations of financial data. This is largely due to improvements in the maturity of the available methods, including graph embedding, graph kernels and deep graph convolutional networks. This has resulted in a number of impressive applications of graph-based methods for data analysis in the finance and business sectors. Because of the timeliness of this topic, this special issue will focus on the recent advances in graph-based pattern recognition approaches in the finance domain. Over the past decade or so, the effectiveness of graph-based methods has been repeatedly demonstrated for modeling the complex structural relationships that exist in high volume and high dimensional data. In the meantime, the size and dimension of data encountered in the finance and business sectors that need to be analyzed have grown dramatically. Despite their attractive features, graph-based pattern recognition methods are still far from being a panacea for extracting or mining relevant information from financial and business data. In addition, because financial data is often time-varying, high-dimensional, unstable, and often noisy or imbalanced, it brings with additional challenges for developing efficient and effective graph-based pattern recognition techniques. Provided these problems can be controlled, graph-based pattern recognition holds out the potential as a powerful tool for modelling complex structural data relationships, and also mining both useful information and temporal patterns which could be used for building powerful analytics for use by financial and commercial organizations. These approaches will thus significantly benefit financial market analysis, banking, and e-commerce, not only for predicting factors such as accurate financial behavior prediction and risk management, but also fraud and anomalous behavior detection.