Simulation of Social Media-Driven Bubble Formation in Financial Markets using an Agent-Based Model with Hierarchical Influence Network

TL;DR

An agent-based model of financial markets, where trading agents are embedded in a hierarchical network of communities, and communities influence the strategies and opinions of traders is introduced.

Abstract

We propose that a tree-like hierarchical structure represents a simple and effective way to model the emergent behaviour of financial markets, especially markets where there exists a pronounced intersection between social media influences and investor behaviour. To explore this hypothesis, we introduce an agent-based model of financial markets, where trading agents are embedded in a hierarchical network of communities, and communities influence the strategies and opinions of traders. Empirical analysis of the model shows that its behaviour conforms to several stylized facts observed in real financial markets; and the model is able to realistically simulate the effects that social media-driven phenomena, such as echo chambers and pump-and-dump schemes, have on financial markets.

Figures (7)

• Figure 1: Sample runs showing how price volatility and fundamental deviation increases with hierarchy strength, $b$.
• Figure 2: PWY procedure on hierarchical model identifies explosive periods (shaded yellow) that are prolonged (left), and clustered in time (right).
• Figure 3: Opinion distributions within the chartist population reveals strong herding tendencies (at T=175-300; 450-700; 1175-1350).
• Figure 4: Parameter set IV. Volatility and explosive behaviour both increase with network efficiency, $\phi$.
• Figure 5: Sample run of the asymmetric echo chamber scenario, showing a volatile asset price that remains consistently above the fundamental.