Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

When do prophets profit in prediction markets?

Source

arXiv

arxiv.org/abs/2607.06166v1

Read the source

Source

Plain-Language Brief

Researchers propose a betting strategy that ensures profit when a forecaster's predictions outperform market prices under certain conditions. The strategy is shown to be the only one with such a robust profitability guarantee, and it was tested successfully in a live deployment on Kalshi.

What the Document Says

  • The study discusses prediction markets and their use in forecasting uncertain events.
  • Classical theory suggests a link between forecasting accuracy and trading profit for a specific market maker design, but this isn't the case for most exchanges today.
  • The authors establish a formal equivalence between predictive accuracy and profitability for any strictly proper scoring rule.
  • They introduce a 'proper' betting strategy that depends on the forecaster's prediction and market price, earning positive expected profit when the forecaster outperforms the market under the given scoring rule and the market has sufficient liquidity.
  • The proof involves a decomposition of expected profit that generalizes the classical AMM guarantee and explains how strategies can profit without an accuracy edge.
  • Empirical testing across AI models shows that proper betting is the only strategy that reliably converts accuracy into profit.
  • The study identifies forecasting personas and demonstrates how the optimal proper strategy varies across them.
  • A live deployment on Kalshi achieved a return on investment of +80.33% with a Sharpe ratio of 3.35.

Key Concepts Mentioned

  • prediction markets
  • forecasting accuracy
  • trading profit
  • strictly proper scoring rule
  • proper betting strategy
  • liquidity
  • AI models
  • forecasting personas

Claims Made by the Document

  • There is a discrepancy between forecasting accuracy and trading profit in most prediction markets today.
  • The authors establish a formal equivalence between predictive accuracy and profitability for any strictly proper scoring rule.
  • Proper betting is the only strategy with a robust profitability guarantee when a forecaster outperforms the market under the given scoring rule and the market has sufficient liquidity.
  • Empirical testing across AI models shows that proper betting is the only strategy that reliably converts accuracy into profit.

Evidence Used

  • The study provides a mathematical proof for the equivalence between predictive accuracy and profitability.
  • The authors present empirical results from testing thousands of forecasts by AI models.

Methods / Approach

  • mathematical proof
  • empirical testing

Limitations Stated by the Authors

Not stated in source

Limitations Noted by the Agent

Agent interpretation — not from the source.

  • The study assumes a sufficient level of liquidity in the market.
  • The findings may not apply to markets with different liquidity levels or structures.

Open Questions

  • How does the proposed strategy perform in markets with varying levels of liquidity?

Notes for Future Q&A

May include interpretation. Labeled where it does.

  • The study focuses on prediction markets, but it's important to note that these markets are just one type of information market.
  • While the study shows a robust profitability guarantee for proper betting, it does not discuss potential risks or downsides associated with such strategies.

Raw Abstract / Excerpt

Prediction markets aggregate dispersed beliefs into prices that act as probabilistic forecasts of uncertain events. Classical theory establishes a clean equivalence between forecasting accuracy and trading profit, but only for the specific automated market maker (AMM) design. However, the largest exchanges today are based on central limit order books in which informed forecasters routinely lose money while uninformed strategies can profit on simple heuristics. We resolve this discrepancy by establishing a formal equivalence between predictive accuracy and profitability. For any strictly proper scoring rule $S$, we exhibit a 'proper' betting strategy that depends only on the forecaster's prediction $\mathbf{p}$ and the market price $\mathbf{q}$, and earns positive expected profit whenever $\mathbf{p}$ outperforms $\mathbf{q}$ under $S$ and the market has sufficient liquidity. Moreover, this proper betting is essentially the only strategy with such robust profitability guarantee. The proof rests on a decomposition of expected profit that strictly generalizes the classical AMM guarantee and also explains how strategies can profit without an accuracy edge. Empirically, across thousands of forecasts by AI models, proper betting is the only strategy that reliably converts accuracy into profit, and we further identify systematic forecasting personas and show how the optimal proper strategy varies across them. A month-long live deployment on Kalshi achieves $+80.33%$ return on investment with a Sharpe ratio of $3.35$.