Newest papers

What Prediction-Market Contracts Reveal at Launch: Trading Volume and Dispute Risk

Ahmed Mahrous, Roberto Di Pietro · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29578 · cited by 0 works (OpenAlex) · open-access PDF

Korean

2023년 1월부터 2026년 5월 사이에 Polymarket에 나열된 802,863개의 분쟁이 거의 정렬된 논란을 사용하여 리스팅에서 유효한 정보( 시장의 제목과 설명, 해상도 출처, 계약 메타데이터)를 사용하면 평생 거래량을 예측하고 나중에 합의가 논의되는지 예측합니다. 계약 정보는 거래량을 정확하게 예측합니다(예형 계약 $R^2 = 로그 볼륨을위한 $0.047$) 그리고 신경 텍스트 모델은 대부분 해석할 수 있습니다: 시장 주제는 가장 큰 이익을 제공합니다($0.289$R^2$이 $0.220의 계약 특성 기준을 넘어), 문구 및 해상도 설계는 거래량에 대한 사례가 $1,0에 도달하는지

Machine translation (Meta M2M100); the English original follows.

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a decomposition attributes more of it to a changed relationship between contract characteristics and demand than to an outdated mapping from text to features.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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Settlement (finance), Ranking (information retrieval), Volume (thermodynamics), Dispute resolution, Listing (finance), Rank (graph theory)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange