ForesightFlow: An Information Leakage Score Framework for Prediction Markets
Maksym Nechepurenko · 2026 · Preprint · SSRN / arXiv
Abstract
ForesightFlow is an Information Leakage Score framework for detecting informed trading on decentralized prediction markets. For an event-resolved binary market, the score quantifies the fraction of the terminal information move priced in before the public news event. Three operational scope conditions are stated as preconditions for interpretation, and the score has a Murphy-decomposition reading that connects label generation to the proper-scoring-rule literature. A pilot evaluation shows that a resolution-anchored proxy for the public-event timestamp is a binding constraint and that documented Polymarket insider cases are systematically deadline-resolved. This motivates a deadline-ILS extension anchored at the public-event timestamp and equipped with a per-category exponential hazard baseline. The FFIC inventory, resolution-typology classification, and code are released openly.
Related tracks
Cite this work
@online{nechepurenko2026_ilsframework,
author = {Nechepurenko, Maksym},
title = {ForesightFlow: An Information Leakage Score Framework for Prediction Markets},
date = {2026-04-30}, doi = {10.2139/ssrn.6687361}, url = {https://ssrn.com/abstract=6687361},
eprint = {2605.00493}, eprinttype = {arxiv}, pubstate = {preprint}
}