Game Analysis of Financial Regulation in International Financial Crisis using Multi-view Graph Convolutional Network

Abstract

The concept of "game analysis" generally refers to the study and assessment of video games, frequently from the viewpoints of player experience, story, mechanics, design, and other relevant variables. It can be used for a variety of games, such as sports, board, card, and video games. A sudden drop in the value of assets or financial institutions is referred to as a financial crisis. It frequently causes the regular operation of financial markets to be interrupted and may have negative impacts on the economy as a whole. In this manuscript, Game Analysis of Financial Regulation in International Financial Crisis using Multi-view Graph Convolutional Network (GA-FR-IFC-MGCN). The proposed method comprises of four phases: dataset, pre-processing, feature selection, classification. Initially, the data is taken from Analcat dataset. Then, Federated Neural Collaborative Filtering (FNCF) method is used to enhancing the networks data. For feature selection phase, the ideal features are chosen by Siberian Tiger Optimization (STO). After, the Multi-view graph convolutional network (MGCN) method is used to classifying international financial crisis as bankruptcy and Non-bankruptcy. In general, MGCN does not express some adaption of optimization strategies for determining optimal parameters to promise exact classification of International Financial Crisis. Therefore, Harbor Seal Whiskers Optimization Algorithm is proposed to enhance weight parameter of MGCN classifier, which precisely predicts the International Financial Crisis. The proposed technique is executed and efficiency of GA-FR-IFC-MGCN depend classification framework is assessed by support of numerous performances evaluating metrics likes accuracy, recall, precision, FI-score, specificity. Finally the performance of proposed GA-FR-IFC-MGCN methods provides 25.32%, 29.30% and 27.32% higher accuracy, 22.41%, 29.30% and 24.31% higher specificity and 25.71%, 27.12% and 25.31% higher precision though analyzed with existing method likes game analysis of financial supervision in international financial crisis(GA-FS-IFC), performance evaluation of clustering techniques for financial crisis prediction(PE-CT-FC) and modified grey wolf optimizer with sparse auto-encoder for financial crisis prediction in small marginal firms (MGWO-SA-FCP) respectively.