The Axiomatic Trader: Latent Regularity, Information Budgets, and the Canonical Form of a Quantitative Investment System
2026-08-24 • Machine Learning
Machine Learning
AI summaryⓘ
The authors explain systematic trading as based on the belief that patterns seen in past data will continue. They model this idea as a fixed process influenced by a hidden state, which leads researchers to identify five key constants that define the system's behavior. These constants help outline how a reliable quantitative investment strategy should be structured. Essentially, the authors show that once these values are known, the design of a good trading system becomes almost determined.
systematic tradinglatent statetime invariancerecurrence boundinvariance defectcoherence timesignal ceilingquantitative investmentregime switching
Authors
Jiayu Li
Abstract
Systematic trading rests on one article of faith: that regularities found in the past persist. We state it as a time-invariant mechanism driven by an unobserved latent state, and show that it leaves a researcher five constants to declare --- the recurrence bound $Lambda$ at a block length $b$, the invariance defect $epsilon_0$ of the representation it is declared of, the coherence times $ell_i$ of the state's coordinates, the signal ceiling $rho$ and the fraction $kappa$ of it contingent on the regime --- after which the architecture of a correct quantitative investment system is nearly forced.