Paper: arXiv 2610.29578

Authors: Ahmed Mahrous, Roberto Di Pietro

Abstract

Using a near-census of 802,863 resolved markets listed on Polymarket between January 2023 and May 2026, and only information available at listing (the market’s title and description, named resolution source, and contract metadata), we predict lifetime trading volume and whether settlement is later disputed. Contract information predicts trading volume well (out-of-sample $R^2 = 0.747$ for log volume), and most of the signal is interpretable: market topic provides the largest gain ($+0.289$ $R^2$ over a $0.220$ contract-feature baseline), wording and resolution-rule design add smaller but measurable improvements ($+0.027$ combined), and neural text models add little beyond the interpretable features. This performance does not survive a period of platform change coinciding with a shift in listing formats: accuracy in predicting whether a market reaches $1,000 falls from AUC $0.940$ under same-period evaluation to $0.577$ when training on past quarters and testing on later ones. The loss concentrates in markets whose question forms were absent from training (76.9% of test markets; on familiar forms the model still reaches $0.778$), and a decomposition attributes more of it to a changed relationship between contract characteristics and demand than to an outdated mapping from text to features. Dispute predictors are more stable but less precise: launch-time features rank dispute risk far better than chance (AUC $0.78$), yet at a 0.31% base rate precision is too low for case-by-case prediction (average precision $0.012$), so the scores suit ranking groups of markets rather than forecasting individual disputes.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 8.0/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper presents a robust empirical analysis of prediction market data, utilizing a large dataset and rigorous statistical methods. While the mathematical complexity is moderate, the novelty lies in applying machine learning and NLP to predict market outcomes and dispute risk from contract launch information. The study is well-written and provides actionable insights.

Research Flowchart

  flowchart TD
    A[Research Goal: Predict Trading Volume & Dispute Risk] --> B{Data: Polymarket Contracts (Jan 2023 - May 2026)};
    B --> C[Methodology: Feature Engineering from Title, Description, Resolution Source, Metadata];
    C --> D{Computational Process: Model Training (Regression for Volume, Classification for Dispute)};
    D --> E[Outcome 1: High Volume Prediction Accuracy (R² = 0.747 log volume)];
    D --> F[Outcome 2: Interpretable Features (Market Topic +0.289 R², Wording/Rules +0.027)];
    D --> G[Outcome 3: Model Instability Post-Platform Change (AUC for $1k volume drops from 0.940 to 0.577)];
    D --> H[Outcome 4: Dispute Risk Ranking (AUC 0.78), but Low Case-by-Case Precision];