Paper: arXiv 2605.00864

Authors: Guang Cheng, Jiaxin Yang, Haoxuan Zou

Abstract

While decentralized prediction markets like Polymarket have gained significant traction, their market microstructure and high-frequency pricing efficiency remain underexplored. This paper conducts a systematic empirical analysis of algorithmic arbitrage within Polymarket’s NBA game markets. By reconstructing continuous market states from over 75 million limit order book snapshots across 173 games, we evaluate the frequency, duration, and profitability of both single-market and combinatorial arbitrage opportunities. Our findings demonstrate profound microstructural efficiency. Single-market anomalies are exceedingly rare, yielding only 7 executable in-game episodes that persist for a median duration of just 3.6 seconds. Combinatorial inefficiencies are more frequent, producing 290 active episodes overwhelmingly concentrated in the final minutes of live play. While combinatorial execution yields a statistically meaningful median return of 101 basis points, we find that the theoretical “Middle” jackpot is never empirically realized. Furthermore, execution is severely bottlenecked by shallow order book depth, with 76.9% of combinatorial opportunities constrained to an average executable size of just 14.8 shares. Ultimately, while executable mispricings exist, they are structurally bounded by liquidity, confining risk-free extraction strictly to the retail scale.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 6.0/10 (capped from 9.0: no out-of-sample test; see penalty flags)
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper is focused on high-frequency data engineering and market microstructure analysis rather than complex mathematical modeling, relying on 75 million order book snapshots to empirically test arbitrage profitability. Its strength lies in its procedural rigor and data-heavy methodology rather than theoretical derivation.

Research Flowchart

  flowchart TD
    A[Research Goal: Efficiency of Arbitrage in Polymarket NBA Markets] --> B(Data Input: 75M+ LOB Snapshots across 173 Games)
    B --> C{Computational Analysis}
    C --> D[Identify Single vs. Combinatorial Arbitrage]
    C --> E[Evaluate Profitability and Execution Constraints]
    D --> F((Key Findings))
    E --> F
    F --> G[Microstructural Efficiency: Opportunities are rare, short-lived, and bottlenecked by low liquidity]

Cited References (8)

  1. Unravelling the Probabilistic Forest: Arbitrage in Prediction Markets — → 2508.03474
  2. Polymarket 101 (2026)
  3. Polymarket API (2026)
  4. Polymarket Volume Is Being Double-Counted (2025)
  5. Polymarket OrderFilled Data (2026)
  6. Price Discovery and Trading in Prediction Markets (2025)
  7. The Limits of Arbitrage (1997)
  8. The Anatomy of Polymarket : Evidence from the 2024 Presidential Election (2026)

1 of 8 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.