Topological Compression of Prediction Market Belief States for Event Forecasting

Aadit Jerfy

Home/Archive/arXiv

arXiv · 2610.25756

Topological Compression of Prediction Market Belief States for Event Forecasting

Aadit Jerfy

View original source ↗Read source document ↗Export metadata ↓

Abstract

Topological Data Analysis (TDA) and Persistent Homology (PH) have been utilized in numerous fields$-$from protein modeling to financial analysis$-$to understand the underlying structure of data. In this paper, we incorporate TDA and PH into forecasting models over a prediction market universe to determine whether the belief state of such markets forms an underlying structure whose shape can provide predictive insight. We conclude that single-parameter PH is able to improve predictive ability and calibrated accuracy of linear forecasting models, while two-parameter multipersistence produces similar benefits for nonlinear models.

Explore related subjects

q-fin.TR

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Aadit Jerfy. 2026-10-19. Topological Compression of Prediction Market Belief States for Event Forecasting. https://arxiv.org/abs/2610.25756

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Combinatorial Arbitrage in Prediction Markets

We develop a framework to identify and quantify arbitrage across logically related prediction-market contracts. We prove that prices outside the convex hull of admissible payoff vectors admit arbitrage and identify optimal arbitrage portfolios through integer programming. Using venue metadata and semantic analysis of resolution criteria, we recover 1.9 million logical relations and compile them into constraint systems covering more than 255,000 contracts. We replay full-depth Polymarket order books to simulate an arbitrageur executing these portfolios against resting orders. Among settled portfolios, an ideal arbitrageur that takes the full displayed depth of every opportunity and reuses its capital at resolution earns a risk-free return of 3.5% a week after spreads and fees. We find that arbitrage opportunities persist longer and attract less observed participation where relation discovery and execution are more costly.

q-fin.TR↗

arXiv2026

Basis-Only Funding Is Not Dividend Fair: Settlement Design in Crypto Equity Perpetuals

Crypto venues increasingly list perpetual futures on equities and other real-world assets (RWAs), which trade continuously yet reference dividend-paying stocks: a long equity perpetual marked to the ex-dividend cash price bears the ex-dividend drop without receiving the dividend. We ask whether the premium-index funding architecture these venues run -- funding set from the contemporaneous basis $e_t=P_t-S_t$ rather than a carry target -- can replicate shareholder cash flows for traders entering and exiting at arbitrary times. It cannot. Funding serves two roles that coincide for non-dividend crypto assets but split apart for equities: basis control and settlement. We give the fair-funding identity, cast timing fairness as an optimal-stopping condition, and characterize when the basis is a sufficient statistic for the fair target. The decisive obstruction is measure-theoretic: a predictable dividend is an atom, and no absolutely continuous funding path can replicate an atom over holding intervals even in the weak limit, so fairness must match the atom with an atom -- an event credit. Exchange-native data confirm this: at each covered ex-date one venue posts a discrete funding atom equal to $-D/(\mathrm{Mark}-D)$ while a standard premium-index venue posts none, transferring the dividend across venues -- from native funding alone, with no external spot.

q-fin.TR↗

arXiv2026

Cross-product Modelling in Continuous Intraday Electricity Markets via Hawkes Processes

As renewable energy integration accelerates, intraday continuous (IDC) electricity markets have become essential for short-term balancing. However, the simultaneous trading of overlapping contracts with varying granularities creates complex, hidden liquidity dependencies that are critical to market stability but remain poorly understood. This paper proposes a multivariate State-Dependent Hawkes Process (SDHP) to model cross-product liquidity dynamics between Quarter-Hourly and Hourly IDC contracts. To determine how cross-product effects vary under different market conditions, we classify the trading sessions into two distinct regimes: 'Normal' and 'Stressed', based on a composite metric of the bid-ask spread, mid-price volatility and queue imbalance. The model is calibrated on the first month of each quarter of 2024 using level 3 limit order book (LOB) data from the Dutch EPEX SPOT IDC market. We find that order flow is overwhelmingly self-driven, with roughly 95\% of orders arriving in reaction to earlier orders in both regimes. Cross-excitation runs mainly from the Quarter-Hourly to the Hourly contract, but this leadership weakens under stress: the ratio of cumulative cross-excitation falls from 2.8 to 1.5, so the two contracts influence each other almost equally. Stress also makes the Quarter-Hourly to Hourly channel much faster, cutting its mean lag from 6.05 to 0.93 seconds. The strong seasonal variation found in calm periods largely disappears under stress, where all four months converge to the same structure.

q-fin.TR↗