Fast Times, Slow Times: Timescale Separation in Financial Timeseries Data

Paper: arXiv 2601.11201

Authors: Jan Rosenzweig

Abstract

Financial time series exhibit multiscale behavior, with interaction between multiple processes operating on different timescales. This paper introduces a method for separating these processes using variance and tail stationarity criteria, framed as generalized eigenvalue problems. The approach allows for the identification of slow and fast components in asset returns and prices, with applications to parameter drift, mean reversion, and tail risk management. Empirical examples using currencies, equity ETFs and treasury yields illustrate the practical utility of the method.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 5.5/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents an interesting application of time-lagged Independent Component Analysis (tICA) and high-moment generalizations to financial time series. While the empirical validation across FX, ETFs, and Treasuries demonstrates good out-of-sample persistence, the analysis lacks comprehensive statistical backtesting or trading strategy performance metrics.

Research Flowchart

  flowchart TD
    A[Research Goal: Separate Fast & Slow Timescales in Financial Data] --> B[Data Inputs: Currencies, Equity ETFs & Treasury Yields]
    B --> C[Apply Variance & Tail Stationarity Criteria]
    C --> D[Formulate & Solve Generalized Eigenvalue Problems]
    D --> E[Isolate Slow Processes & Fast Processes]
    E --> F[Outcomes: Improved Parameter Drift, Mean Reversion & Tail Risk Management]