ForesightFlow
← Research

Microstructure

We adapt classical market-microstructure theory — PIN, VPIN, Kyle's λ, order imbalance, and variance-ratio diagnostics — to the discrete-outcome, on-chain CLOB structure of decentralized prediction markets.

What we ask

  • —How does informed trading manifest differently in binary-outcome markets compared to continuous-price equity markets?
  • —Can VPIN be computed in real time from on-chain trade data without access to quote history?
  • —What wallet-level features predict informed trading independent of price-impact signals?
  • —How does liquidity dynamics change in the hours before a market resolves?

How we approach it

  • —Trade-level microstructure estimation (PIN, VPIN, Kyle's λ) adapted for binary CLOBs
  • —On-chain wallet fingerprinting: novelty score, funding graph analysis, cross-market behavior
  • —Variance-ratio and autocorrelation analysis of intraday price series
  • —Event-study methodology using documented insider-trading episodes as ground truth

Market microstructure is the study of how prices are formed through the trading process — the mechanics beneath the efficient-market surface. On prediction markets, this process is uniquely transparent: every trade, every wallet, every order is on-chain and auditable.

This transparency creates both opportunity and responsibility. We can measure informed trading with a precision impossible in traditional markets. But the same techniques that detect informed flow can, if published carelessly, help bad actors evade detection. We publish methods at a level of abstraction that advances the field without providing a free evasion guide.

Publications in this track

Datasets

FFIC — ForesightFlow Insider Cases

A curated validation set mapping eight publicly documented episodes of suspected informed trading on Polymarket to concrete on-chain market identifiers. Cases span 2023–2026 and cover 24 individual markets across military and geopolitical actions, corporate proprietary disclosures, and regulatory decisions.

pmxt-behavioral-clusters-v1 — PMXT Behavioral Clusters v1 — Non-Retail Polymarket Microstructure Dataset

Fill-side behavioral clusters, feature tiers, and per-market microstructure signatures from 13.36M OrderFilled events on Polymarket CTFExchange (43,116 markets, 77,203 addresses, 2026-04-21 to 2026-04-27). k-means k=5 archetypes, 6 feature tiers, Spearman bilateral analysis with BH-FDR correction. Bundle 3 of the PMXT family; companion to Paper 4 of the Event-Linked Perpetuals research programme.

pmxt-stylized-facts-v1 — Polymarket Stylized Facts Dataset

Per-market stylized-fact measurements (SF1–SF9) for 13,314 resolved Polymarket binary-event markets over 2026-04-21 to 2026-04-27. Empirical foundation for Paper 1 of the Event-Linked Perpetuals research programme.