Paper: arXiv 2510.15205

Authors: Shaw Dalen

Abstract

Prediction markets, such as Polymarket, aggregate dispersed information into tradable probabilities, but they still lack a unifying stochastic kernel comparable to the one options gained from Black-Scholes. As these markets scale with institutional participation, exchange integrations, and higher volumes around elections and macro prints, market makers face belief volatility, jump, and cross-event risks without standardized tools for quoting or hedging. We propose such a foundation: a logit jump-diffusion with risk-neutral drift that treats the traded probability p_t as a Q-martingale and exposes belief volatility, jump intensity, and dependence as quotable risk factors. On top, we build a calibration pipeline that filters microstructure noise, separates diffusion from jumps using expectation-maximization, enforces the risk-neutral drift, and yields a stable belief-volatility surface. We then define a coherent derivative layer (variance, correlation, corridor, and first-passage instruments) analogous to volatility and correlation products in option markets. In controlled experiments on synthetic risk-neutral paths and real event data, the model reduces short-horizon belief-variance forecast error relative to diffusion-only and probability-space baselines, supporting both causal calibration and economic interpretability. Conceptually, the logit jump-diffusion kernel supplies an implied-volatility analogue for prediction markets: a tractable, tradable language for quoting, hedging, and transferring belief risk across venues such as Polymarket.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces advanced stochastic processes (logit jump-diffusion, expectation-maximization calibration) and derivative pricing PIDEs, indicating high mathematical complexity. It validates the model on synthetic data and real event data with quantitative forecast error metrics, supporting empirical rigor, though it lacks full implementation details like code or public datasets.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Develop Black-Scholes equivalent<br>for prediction markets"] --> B["Methodology<br>Logit Jump-Diffusion Model"]
  B --> C["Data & Inputs<br>Synthetic Risk-Neutral Paths<br>Real Event Data"]
  C --> D["Computational Process<br>EM Calibration &<br>Belief Volatility Surface"]
  D --> E["Key Findings<br>Reduced Forecast Error &<br>Tradable Belief Risk Factors"]

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 proposes a minimal, actionable kernel: a logit jump‑diffusion with risk‑neutral drift that treats the traded probability as a Q‑martingale and exposes belief volatility, jump intensity, and cross‑event dependence as quotable risk factors.

Source sentence
We propose a minimal, actionable kernel: a logit jump–diffusion with multi-event correlation. Let pt ∈(0, 1) be the risk-neutral event probability and xt = log(pt/(1 −pt)) its log-odds. We model xt as a correlated jump–diffusion. Enforcing the martingale property of pt under the risk-neutral measure pins down the drift

Assumes 6

  • The traded price pt is a risk‑neutral probability and a Q‑martingale. model
    Source sentence
    treats the traded probability pt as a Q‑martingale
  • Microstructure noise is heteroskedastic and can be modeled as a function of observable frictions. statistical
    Source sentence
    Model σ2 η(t) as a function of observable frictions (spread st, depth dt, trade rate rt, aggressor imbalance ιt)
  • Diffusion and jump components can be separated via an EM algorithm. model
    Source sentence
    separates diffusion from jumps via EM
  • A Gaussian state‑space filter (Kalman filter) is sufficient to recover the latent logit x. statistical
    Source sentence
    A standard Kalman filter/smoother suffices; if p is pinned near 0/1 for long stretches or if jumps are very frequent, an Unscented KF or particle smoother is more stable.
Show 2 more
  • Risk‑neutral drift is enforced after EM to ensure martingale property. model
    Source sentence
    after EM (below) enforces the risk‑neutral drift (3)
  • Event contracts pay a fixed $1 payoff if the outcome occurs, otherwise $0. market
    Source sentence
    An event contract is a yes/no claim with a fixed payoff: it pays $1 if the specified outcome occurs by a given date and $0 otherwise.

Data

  • Polymarket high‑volume event trades · Polymarket market-prices unknown
    20 high‑volume event trades
    Source sentence
    To stress‑test models with known ground truth and realistic frictions, we use 20 high‑volume event trades from Polymarket.
  • Synthetic RN‑consistent path synthetic unknown
    Source sentence
    Table 1 reports causal H=60 s forward‑sum forecasts of next‑window realized logit variance on the synthetic RN‑consistent path.

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • The RN‑JD model achieves the lowest overall MSE (70.28) and QLIKE (1.46) among all baselines, indicating superior forecast accuracy of belief‑volatility. performance
    Source sentence
    RN‑JD attains MSEall=70.28 and QLIKEall=1.46, representing a consistent improvement over both diffusion‑based and p‑space volatility models.
  • The model reduces short‑horizon belief‑variance forecast error relative to diffusion‑only and probability‑space baselines. predictive-accuracy
    Source sentence
    the model reduces short‑horizon belief‑variance forecast error relative to diffusion‑only and probability‑space baselines

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 20 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

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

Cited References (92)

  1. Logarithmic Market Scoring Rules for Modular Combinatorial Information Aggregation (2003)
  2. A Utility Framework for Bounded-Loss Market Makers (2012) — link
  3. Efficient Market Making via Convex Optimization, and a Connection to Online Learning (2013)
  4. A Practical Liquidity-Sensitive Automated Market Maker (2010)
  5. Improved Price Oracles: Constant Function Market Makers (2020) — link
  6. Uniswap v2 Core Whitepaper (2020)
  7. Limit Order Books (2013)
  8. The Pricing of Options and Corporate Liabilities (1973)
and 84 more
  1. Option Pricing When Underlying Stock Returns are Discontinuous (1976)
  2. A Closed-Form Solution for Options with Stochastic Volatility (1993)
  3. Pricing with a Smile (1994)
  4. The Volatility Surface: A Practitioner’s Guide (2006)
  5. Information-Based Asset Pricing (2007) — link
  6. The Jacobi Stochastic Volatility Model (2016) — link
  7. Exact Simulation of the Wright–Fisher Diffusion (2017)
  8. Measuring the Information Content of Stock Trades (1991)
  9. A Microstructure Estimate of Realized Volatility (2006)
  10. On the Functional Estimation of Jump–Diffusions (2001)
  11. Likelihood Evaluation of Jump–Diffusion Models Using Deterministic Nonlinear Filters (2019) — link
  12. Testing for Common Arrivals of Jumps for Discretely Observed Multidimensional Processes (2009)
  13. Prediction Markets (2004) — link
  14. Interpreting Prediction Market Prices as Probabilities (2006) — link
  15. Interpreting the Predictions of Prediction Markets (2004) — link
  16. The Promise of Prediction Markets (2008) — link
  17. Prediction Markets for Economic Forecasting (2012) — link
  18. Combinatorial Information Market Design (2003) — link
  19. A Utility Framework for Bounded-Loss Market Makers (2007) — link
  20. A Practical Liquidity-Sensitive Automated Market Maker (2010) — link
  21. Efficient Market Making via Convex Optimization, and a Connection to Online Learning (2013) — link
  22. Uniswap v2 Core (2020) — link
  23. Improved Price Oracles: Constant Function Market Makers (2020) — link
  24. Bid, Ask and Transaction Prices in a Specialist Market with Heterogeneously Informed Traders (1985) — link
  25. Continuous Auctions and Insider Trading (1985) — link
  26. A Guide to Volatility and Variance Swaps (1999) — link
  27. Volatility Derivatives (2009) — link
  28. The Effect of Jumps and Discrete Sampling on Volatility and Variance Swaps (2008) — link
  29. Option Pricing When Underlying Stock Returns Are Discontinuous (1976) — link
  30. The Jacobi Stochastic Volatility Model (2018) — link
  31. On the W right– F isher Model of Genetic Drift (2008) — link
  32. Time Series Analysis by State Space Methods (2012)
  33. Maximum Likelihood from Incomplete Data via the EM Algorithm (1977)
  34. Prediction Markets (2004) — link
  35. Interpreting Prediction Market Prices as Probabilities (2006) — link
  36. Interpreting the Predictions of Prediction Markets (2004) — link
  37. The Promise of Prediction Markets (2008) — link
  38. Prediction Markets for Economic Forecasting (2012) — link
  39. The Geometry of Constant Function Market Makers — → 2308.08066
  40. Bid, Ask and Transaction Prices in a Specialist Market with Heterogeneously Informed Traders (1985) — link
  41. Continuous Auctions and Insider Trading (1985) — link
  42. An Analysis of Uniswap Markets (2019) — link
  43. Decentralized Exchanges: The Profitability Frontier of Constant Product Market Makers — → 2302.05219
  44. A Guide to Volatility and Variance Swaps (1999) — link
  45. Volatility Derivatives (2009) — link
  46. The Effect of Jumps and Discrete Sampling on Volatility and Variance Swaps (2008) — link
  47. L 'e vy Processes and Stochastic Calculus (2009) — link
  48. Applied Stochastic Control of Jump Diffusions (2005) — link
  49. Financial Modelling with Jump Processes (2004) — link
  50. A Jump-Diffusion Model for Option Pricing (2002) — link
  51. Pricing Options on Realized Variance (2004) — link
  52. Pricing and Hedging Volatility Derivatives (2008) — link
  53. Corridor Variance Swap (2008) — link
  54. Efficient Pricing and Super Replication of Corridor Variance Swaps (2017) — link
  55. Empirical Market Microstructure: The Institutions, Economics, and Econometrics of Securities Trading (2007) — link
  56. Ultra High Frequency Volatility Estimation with Dependent Microstructure Noise (2005) — link
  57. Theory of Rational Option Pricing (1973)
  58. Event Contracts (2024) — link
  59. Contracts & Products: Event Contracts (2024) — link
  60. Polymarket gets big investment from New York Stock Exchange parent company (2025) — link
  61. Polymarket discloses past funding rounds totaling $205 million before $2 billion ICE investment (2025) — link
  62. ICE Announces Strategic Investment in Polymarket (2025) — link
  63. NYSE parent to invest up to $2bn in prediction platform Polymarket (2025) — link
  64. NYSE owner takes $2 billion stake in Polymarket as prediction markets go mainstream (2025) — link
  65. `Golden Age’ of Prediction Markets Dawns as Activity Reaches New Highs (2025) — link
  66. Sports Trading Pushes Kalshi Past All-Time Volume Records (2025) — link
  67. Kalshi Prediction Markets Are Pulling In $1 Billion Monthly as State Regulators Loom (2025) — link
  68. CFTC Issues Proposal on Event Contracts (2024) — link
  69. Event Contracts (Notice of Proposed Rulemaking) (2024) — link
  70. KalshiEX LLC v.\ CFTC, No.\ 24-5205 (D.C. Cir.\ 2024) (2024) — link
  71. The Use of Knowledge in Society (1945) — link
  72. Corporate Prediction Markets: Evidence from Google, Ford, and Firm X (2015) — link
  73. Pentagon Drops Bid For Futures Market (2003) — link
  74. The Policy Analysis Market (PAM): A Thwarted Experiment in the Use of Prediction Markets for Public Policy (2007) — link
  75. 7 U.S. Code S 13-1: Onion Futures Act (1958) (1958) — link
  76. An Evaluation of 2016 Election Polls in the U.S. (2017) — link
  77. High-frequency trading in a limit order book (2008)
  78. Algorithmic and High-Frequency Trading (2015)
  79. Empirical Market Microstructure (2007)
  80. Time Series Analysis by State Space Methods (2012)
  81. A New Extension of the Kalman Filter to Nonlinear Systems (1997)
  82. Jumps in Financial Markets: A New Nonparametric Test (2008)
  83. Power and Bipower Variation with Stochastic Volatility and Jumps (2004)
  84. Approaching human-level forecasting with language models (2024)

2 of 92 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.