Manipulation in Prediction Markets: An Agent-based Modeling Experiment

Paper: arXiv 2601.20452

Authors: Bridget Smart, Ebba Mark, Anne Bastian, Josefina Waugh

Abstract

Prediction markets mobilize financial incentives to forecast binary event outcomes through the aggregation of dispersed beliefs and heterogeneous information. Their growing popularity and demonstrated predictive accuracy in political elections have raised speculation and concern regarding their susceptibility to manipulation and the potential consequences for democratic processes. Using agent-based simulations combined with an analytic characterization of price dynamics, we study how high-budget agents can introduce price distortions in prediction markets. We explore the persistence and stability of these distortions in the presence of herding or stubborn agents, and analyze how agent expertise affects market-price variance. Firstly we propose an agent-based model of a prediction market in which bettors with heterogeneous expertise, noisy private information, variable learning rates and budgets observe the evolution of public opinion on a binary election outcome to inform their betting strategies in the market. The model exhibits stability across a broad parameter space, with complex agent behaviors and price interactions producing self-regulatory price discovery. Second, using this simulation framework, we investigate the conditions under which a highly resourced minority, or ‘‘whale’’ agent, with a biased valuation can distort the market price, and for how long. We find that biased whales can temporarily shift prices, with the magnitude and duration of distortion increasing when non-whale bettors exhibit herding behavior and slow learning. Our theoretical analysis corroborates these results, showing that whales can shift prices proportionally to their share of market capital, with distortion duration depending on non-whale learning rates and herding intensity.

Complexity vs Empirical Score

• Math Complexity: 5.5/10
• Empirical Rigor: 6.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper provides a timely analysis of price manipulation and ‘whale’ dynamics in modern prediction markets using a dual approach of agent-based modeling and analytical characterization. It scores exceptionally well on reproducibility due to open-source code and an interactive Dash application, while striking a strong balance between mathematical formulation and practical simulation.

Research Flowchart

  flowchart TD
    A[Research Goal: Assess Prediction Market Vulnerability to Manipulation by High-Budget 'Whale' Agents] --> B[Inputs: Heterogeneous Expertise, Noisy Private Information, Learning Rates & Budgets]
    B --> C[Methodology: Agent-Based Model & Theoretical Analytics of Price Dynamics]
    C --> D[Simulation: Simulate Elections with Herding, Stubborn, & Biased Whale Agents]
    D --> E[Finding 1: Markets Self-Regulate and Achieve Accurate Price Discovery Baseline]
    D --> F[Finding 2: Whales Distort Prices Proportionally to Capital; Duration Increases with Herding & Slow Learning]

Cited References (59)

1. Explore the Highest Volume Popular Polymarkets — link
2. Kalshi Data and Analytics — link
3. National Polls, Local Preferences and Voters’ Behaviour: Evidence from the UK General Elections (2022) — link
4. Beauty Contests and Iterated Expectations in Asset Markets (2006) — link
5. How much do we learn? Measuring symmetric and asymmetric deviations from Bayesian updating through choices (2025) — link
6. Belief updating: does the ‘good-news, bad-news’ asymmetry extend to purely financial domains? (2021) — link
7. Prediction Market Accuracy in the Long Run (2008) — link
8. Herd Behavior in Financial Markets (2001) — link

0 of 59 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.