Skip to content
All library documents

Online Learning for Statistical Arbitrage Without Stationarity Assumptions

Article arXiv papers · Author: Christopher Mohri
Read the original

Summary

This document introduces an online-learning approach to statistical arbitrage. It contrasts the approach with familiar strategies based on mean-reversion models, whose techniques depend on assumptions that may fail for general non-stationary stochastic processes. The proposed alternative is intended to operate without requiring those assumptions.

The document states that the method has strong learning guarantees, suggesting a theoretical basis for adapting to data as it arrives. However, the description does not specify the algorithm, the precise guarantees, the trading rules, or how portfolio and transaction costs are handled. It also provides no empirical results or comparisons. The contribution is therefore presented as a general methodological alternative; the available information is insufficient to assess its practical profitability or robustness in live markets.

Key ideas

  • Traditional statistical arbitrage often relies on mean-reversion models and their assumptions.
  • Those assumptions may not hold for general non-stationary stochastic processes.
  • The proposed alternative uses online learning and does not require those assumptions.
  • The document claims strong learning guarantees but supplies no details or empirical evaluation.

Tags

ArbitrageMean reversionMachine learningStatistics
Full text
# Online Learning Algorithms for Statistical Arbitrage


# Online Learning Algorithms for Statistical Arbitrage









Statistical arbitrage is a class of financial trading strategies using mean reversion models. The corresponding techniques rely on a number of assumptions which may not hold for general non-stationary stochastic processes. This paper presents an alternative technique for statistical arbitrage based on online learning which does not require such assumptions and which benefits from strong learning guarantees.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.