---
title: Order Flow Imbalance and Price Discovery on Prediction Markets: Evidence from Kalshi
url: https://www.ml-quant.com/papers/ssrn/7520438/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-02
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 7520438
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7520438
featured: 2026-10-02
citations: unknown
topic: Trading, Microstructure & Execution
---


# Order Flow Imbalance and Price Discovery on Prediction Markets: Evidence from Kalshi

Order flow imbalance predicts contemporaneous mid-price changes in Kalshi binary event contracts, with explanatory power varying from 0.29 for sports to 0.02 for macroeconomic events.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7520438
- Identifier: SSRN 7520438
- Released: 2026-09-26
- First featured: Quant Letter No. 133 (2026-10-02): https://www.ml-quant.com/issues/2026-10-02/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Trading, Microstructure & Execution
- Authors: Ash Malék

## Related

- [Unravelling the Probabilistic Forest: Arbitrage in Prediction Markets](https://www.ml-quant.com/papers/arxiv/2508.03474/): Polymarket, a prediction market platform, has shown instances of arbitrage due to mispriced dependent assets, leading to an estimated $40 million in guaranteed profits, a study reveals.
- [Decentralized Prediction Markets and Sports Books](https://www.ml-quant.com/papers/arxiv/2307.08768/): The article suggests a decentralized framework for prediction markets using automated market makers, with a focus on liquidity management and its impact on market behavior.
- [Market Attention and Information Quality in On-Chain Prediction Markets: Evidence from Polymarket](https://www.ml-quant.com/papers/ssrn/7540819/): On-chain prediction market analysis finds 68.2 percent of volume sits in well-calibrated markets with average seven-day pricing error of 0.03.
- [Incentives at Play: Fee-Induced Volume on a Regulated Perpetual Futures Venue](https://www.ml-quant.com/papers/ssrn/7512338/): Analysis of Kalshi's regulated Bitcoin and Ethereum futures reveals that 39-48% of notional trades are mechanical fixed-size orders that vanish when fees are charged, indicating costless artificial volume rather than legitimate trading.
- [Election Arbitrage](https://www.ml-quant.com/papers/ssrn/5086104/): The study shows that prediction markets can help understand the relationship between financial markets and political candidates, with systematic portfolios outperforming the benchmark during election cycles.
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://www.ml-quant.com/papers/arxiv/2501.09747/): A new tokenization scheme, Frequency-space Action Sequence Tokenization (FAST), has been proposed for robot actions, facilitating the training of vision-language action policies for complex and high-frequency tasks.