ForesightFlow: Real-Time Detection of Informed Trading in Decentralized Prediction Markets
Maksym Nechepurenko · 2026 · Working Paper
← Research
On-chain forensics
We develop wallet clustering, funding-flow analysis, novelty scoring, and cross-market behavior methods to attribute trades to economic agents rather than pseudonymous addresses.
What we ask
- —How reliably can on-chain address clustering identify wallets controlled by the same entity?
- —What funding-graph patterns distinguish retail, institutional, and insider-type traders?
- —How does wallet novelty score predict trade informativeness?
- —Can cross-market correlation between wallets reveal coordinated informed trading?
How we approach it
- —Graph-based wallet clustering using funding and interaction edges
- —Novelty scoring: recency, funding source diversity, age-adjusted activity
- —Cross-market wallet co-occurrence analysis
- —OSINT-grounded case studies using documented episodes as validation
Every trade on Polymarket leaves a permanent, public record. The challenge is not access — it is interpretation. Pseudonymous addresses, mixing services, and multi-wallet strategies create noise that requires structured forensic methods to resolve.
Our approach treats on-chain data as a graph problem: wallets are nodes, transactions and funding flows are edges. Cluster membership, centrality, and cross-market co-occurrence tell a story that raw address data cannot.
Publications in this track
Preprint
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.