Evaluation of the Fluctuation Mechanism of Behavioral Financial Market Based on Edge Computing

Abstract

The global economy is growing faster and faster. Behavioral finance is a transformation of financial theory. Over the past decade, this shift has had strong repercussions in academia, challenging the dominance of traditional finance and forming its own theoretical system. With the development of the stock market, traditional financial theories and behavioral financial theories continue to converge, and traditional financial theories based on investor rationality and efficient market assumptions are subject to unprecedented conjectures. Financial markets are affected by subjective factors such as people’s behaviors and emotions. Investors always make decisions based on bounded rationality, cognitive deficits, and, ultimately, rationality. In order to avoid the complex and unpredictable risks of financial markets and understand their changing laws, the analysis of the characteristics of financial instability is conducive to understanding the nature and internal principles of financial markets. Analysis of the volatility characteristics of financial markets must give priority to the analysis of financial chronological order. Financial time series are characterized by differences in financial markets, which are indeterminate orders, and the analysis of their fluctuations becomes crucial for stimulating the microstructure of financial behavior markets. Therefore, in order to give full play to the role of edge computing and promote the controllability of behavioral financial market volatility, this paper used the calculation task load model algorithm, time slot length optimization algorithm, asymmetric thick-tail random fluctuation, and volatility analysis application algorithm to study the subject of how to learn to reduce financial market volatility, summarizing and discussing the experiment. The research results showed that the behavioral financial market volatility mechanism based on edge computing constructed in this paper improved the predictability of financial market volatility by 15%.