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.
The FFIC Inventory is a curated validation set mapping eight publicly documented episodes of suspected informed trading on Polymarket to concrete on-chain market identifiers. It is the companion dataset for ForesightFlow: Real-Time Detection of Informed Trading in Decentralized Prediction Markets.
Why this dataset exists
Published reports on informed trading typically describe events at the narrative level without releasing on-chain identifiers necessary for reproducibility. Every research group has had to reconstruct the case-to-market mapping themselves. FFIC closes this gap.
Coverage
Eight cases spanning 2023–2026, mapped to 24 individual Polymarket markets:
| Case ID | Description | Date | Markets | Total volume |
|---|---|---|---|---|
fficd-001 | 2024 U.S. presidential election | Nov 2024 | 4 | $2.96 B |
fficd-002 | October 2024 Iran strike on Israel | Oct 2024 | 3 | $1.04 M |
fficd-003 | 2026 U.S.–Iran conflict cluster | Feb–Apr 2026 | 6 | $825.3 M |
fficd-004 | Maduro / Venezuela cluster | 2025–2026 | 3 | $70.5 M |
fficd-005 | Bitcoin ETF SEC approval | Jan 2024 | 1 | $12.6 M |
fficd-006 | Google Year-in-Search rankings 2025 | Dec 2025 | 3 | $5.3 M |
fficd-007 | FTX / SBF case cluster | 2024–2025 | 3 | $9.5 M |
fficd-008 | Romanian presidential election 2024–2025 | Dec 2024 | 1 | $326.5 M |
Total: 24 markets, approximately $4.21 billion in cumulative volume.
Format
Distributed as a YAML manifest (ffic-inventory/cases.yaml) with a companion JSON Schema for validation. Per-case evidence files are in ffic-inventory/sources/<case-id>/. Machine-readable formats: ffic-v1.csv and ffic-v1.jsonl.
Intended use
- Validation dataset for ILS-based informed-trading detection
- Benchmarking other anomaly detection methods against documented ground truth
- Training classifiers for insider-trading detection
- Academic study of information leakage in decentralized finance
Citation
@misc{nechepurenko2026ffic,
title = {ForesightFlow Insider Cases (FFIC) Inventory},
author = {Nechepurenko, Maksym},
year = {2026},
publisher = {ForesightFlow / Devnull FZCO},
url = {https://github.com/ForesightFlow/datasets/tree/main/ffic-inventory},
note = {Version 1.0, CC-BY-4.0}
}