Paper: arXiv 2409.00742

Authors: Gonzalo Bohorquez, John Cartlidge

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.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper primarily uses an agent-based model with a hierarchical network, which involves moderate algorithmic complexity but lacks heavy mathematical derivations or formal proofs. Empirical rigor is bolstered by explicit mention of open-source code availability on GitHub and analysis against stylized facts, but it’s based on simulated data rather than backtesting on real market data.

Research Flowchart

  flowchart TD
  A["Research Goal<br>How does a hierarchical<br>network structure model<br>social media-driven bubbles?"] --> B["Methodology: Agent-Based Model<br>- Agents in hierarchical community network<br>- Social media influence dynamics"]
  B --> C["Inputs: Model Parameters<br>- Network hierarchy<br>- Influence weights<br>- Trading rules"]
  C --> D["Computational Process<br>Agent Interaction &<br>Market Simulation"]
  D --> E["Key Findings<br>- Conforms to stylized facts<br>- Simulates echo chambers<br>- Models pump-and-dump schemes<br>- Validates hierarchical structure"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper introduces a hierarchical agent-based model of financial markets that incorporates social‑media driven influence on trader opinions and behaviours.

Source sentence
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.

Assumes 3

  • Only a single asset is traded in the model. model
    Source sentence
    However, our model is limited by some restrictive as-sumptions, such as: only a single asset is traded; every trader is affected by community influences equally; and the number of traders in the market is a fixed constant.
  • Every trader is affected by community influences equally. model
    Source sentence
    However, our model is limited by some restrictive as-sumptions, such as: only a single asset is traded; every trader is affected by community influences equally; and the number of traders in the market is a fixed constant.
  • The number of traders in the market is a fixed constant. model
    Source sentence
    However, our model is limited by some restrictive as-sumptions, such as: only a single asset is traded; every trader is affected by community influences equally; and the number of traders in the market is a fixed constant.

Data

  • Synthetic simulation runs of the hierarchical ABM synthetic unknown
    Source sentence
    Reproducing stylized facts of financial markets Fig. 1 shows sample runs with fixed fundamental value, pf = 10, under increasing values of b (refer to equation (10)). We see that price movements increase in magni-tude as the hierarchy’s effect becomes more pronounced, with the market price displaying sustained and significant deviation from the fundamental price when b is large.

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • Price movements increase in magnitude as the hierarchy’s effect becomes more pronounced, with larger deviations from the fundamental price for higher hierarchy strength (b). statistical
    Source sentence
    We see that price movements increase in magni-tude as the hierarchy’s effect becomes more pronounced, with the market price displaying sustained and significant deviation from the fundamental price when b is large.
  • Mean volatility and the proportion of runs with explosive periods both increase with hierarchy strength, indicating higher volatility and more frequent bubbles under stronger hierarchical influence. statistical
    Source sentence
    Mean volatility and proportion of runs with explosive periods, showing both measures tend to increase with hierarchy strength, b. Volatility Explosive Periods b Set II Set III Set IV Set II Set III Set IV 0.0 4.7 1.6 3.9 0% 4% 0% 0.1 5.9 1.7 3.6 2% 4% 0% 0.25 5.5 2.2 4.0 6% 8% 6% 0.5 5.6 2.1 4.5 4% 12% 6% 1.0 6.7 2.8 5.7 2% 14% 15% 2.0 9.1 4.4 8.9 44% 34% 22% *Cells show mean value of 50 i.i.d. simulation trials,

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 6 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

https://github.com/gonzalo-bo/Lux-Hierarchy — the authors' own repository

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (68)

  1. Cluster Analysis for Applications (1983)
  2. R: A Language and Environment for Statistical Computing (2012) — link
  3. R: A Language and Environment for Statistical Computing (2008) — link
  4. MAPCLUS: A mathematical programming approach to fitting the ADCLUS models (1980 )
  5. Model-Based Gaussian and Non-Gaussian Clustering (1993 )
  6. Euclidean cluster analysis (1969 )
  7. Model-based Clustering with Noise: Bayesian inference and estimation
  8. Numerical taxonomy with fuzzy sets (1974)
and 60 more
  1. \LaTeX : A Document Preparation System (1986)
  2. The \LaTeX Companion (2004)
  3. Agent-based computing from multi-agent systems to agent-based models: a visual survey (2011) — link
  4. Agent-based modeling: Methods and techniques for simulating human systems (2002) — link
  5. On stylized facts of cryptocurrencies returns and their relationship with other assets, with a focus on the impact of COVID-19 (2023) — link
  6. A cryptocurrency empirical study focused on evaluating their distribution functions (2022) — link
  7. Volatility Clustering in Financial Markets: A MicroSimulation of Interacting Agents (2000) — link
  8. A Simple General Approach to Inference about the Tail of a Distribution. (1975) — link
  9. Speculative bubbles and herding in cryptocurrencies (2022) — link
  10. Valuation, liquidity price, and stability of cryptocurrencies (2018) — link
  11. Fundamental and speculative components of the cryptocurrency pricing dynamics (2023) — link
  12. Distribution of the estimators for autoregressive time series with a unit root (1979) — link
  13. Explosive behavior in the 1990s Nasdaq : When did exuberance escalate asset values? (2011) — link
  14. Testing for multiple bubbles: Historical episodes of exuberance and collapse in the S&P 500 (2015) — link
  15. The technology and economic determinants of cryptocurrency exchange rates: The case of Bitcoin (2017) — link
  16. Empirical properties of asset returns: stylized facts and statistical issues (2001) — link
  17. Scaling and criticality in a stochastic multi-agent model of a financial market (1999) — link
  18. Replicating agent-based simulation models of herding in financial markets (MRes Dissertation) (2021)
  19. Volatility clustering in financial markets: a microsimulation of interacting agents (2000) — link
  20. Opinion dynamics and learning in social networks (2011) — link
  21. Modeling opinion dynamics in social networks (2014) — link
  22. Building social media observatories for monitoring online opinion dynamics (2020) — link
  23. Testing for multiple bubbles (2012) — link
  24. Efficient capital markets (1970) — link
  25. Efficiency, multifractality, and the long-memory property of the Bitcoin market: A comparative analysis with stock, currency, and gold markets (2018) — link
  26. Bitcoin and market-(in) efficiency: a systematic time series approach (2019) — link
  27. Stock market volatility and weak-form efficiency: evidence from an emerging market (2009) — link
  28. Emergence of speculation in a hierarchical agent-based model (2023) — link
  29. A hierarchical model of financial crashes (1998) — link
  30. Widespread worry and the stock market (2010) — link
  31. Twitter mood predicts the stock market (2011) — link
  32. The echo chamber effect on social media (2021) — link
  33. All that glitters: The effect of attention and news on the buying behavior of individual and institutional investors (2008) — link
  34. Echo Chambers (2022) — link
  35. Social media, news media and the stock market (2020) — link
  36. The Cryptocurrency “Pump-and-Dump”: Social Media and Legal and Ethical Ambiguity (2022) — link
  37. Cryptocurrency pump-and-dump schemes (2021) — link
  38. Cryptocurrency price drivers: Wavelet coherence analysis revisited (2018) — link
  39. Predicting altcoin returns using social media (2018) — link
  40. How does social media impact Bitcoin value? A test of the silent majority hypothesis (2018) — link
  41. Manias, panics, and crashes: A history of financial crises (2005) — link
  42. Irrational exuberance: Revised and expanded third edition (2015) — link
  43. A theory of fads, fashion, custom, and cultural change as informational cascades (1992) — link
  44. Herd behaviour, bubbles and crashes (1995) — link
  45. Tulipmania: money, honor, and knowledge in the Dutch Golden Age (2019)
  46. Hierarchical structure and the prediction of missing links in networks (2008) — link
  47. Identity and search in social networks (2002) — link
  48. Hierarchical community-level information diffusion modeling in social networks (2017) — link
  49. Evolutionary location and pricing strategies in competitive hierarchical distribution systems: A spatial agent-based model (2013) — link
  50. Simulating the spatial diffusion of memes on social media networks (2019) — link
  51. Network hierarchy in Kirman’s ant model: fund investment can create systemic risk (2009)
  52. A note on institutional hierarchy and volatility in financial markets (2011)
  53. Hierarchical economic agents and their interactions (2016)
  54. How can extremism prevail? A study based on the relative agreement interaction model (2002)
  55. The Relative Disagreement Model of Opinion Dynamics: Where Do Extremists Come From? (2014)
  56. Statistical theory of the continuous double auction (2003)
  57. The causal relationship between social media sentiment and stock return: Experimental evidence from an online message forum (2022) — link
  58. Social Media and Stock Market Participation (2023)
  59. A Hierarchical Communication Network within a Financial Agent-Based Model (2024)
  60. A note on GameStop , short squeezes, and autodidactic herding: An evolution in financial literacy? (2022) — link

0 of 68 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.