Signal from Noise Signal from Noise: A Neural Network-Based Denoising Approach for Measuring Global Financial Spillovers

Paper: arXiv 2509.01156

Authors: Abdullah Karasan, Özge Sezgin Alp

Abstract

Filtering signal from noise is fundamental to accurately assessing spillover effects in financial markets. This study investigates denoised return and volatility spillovers across a diversified set of markets, spanning developed and developing economies as well as key asset classes, using a neural network-based denoising architecture. By applying denoising to the covariance matrices prior to spillover estimation, we disentangle signal from noise. Our analysis covers the period from late 2014 to mid-2025 and adopts both static and time-varying frameworks. The results reveal that developed markets predominantly serve as net transmitters of volatility spillovers under normal conditions, but often transition into net receivers during episodes of systemic stress, such as the Covid-19 pandemic. In contrast, developing markets display heightened instability in their spillover roles, frequently oscillating between transmitter and receiver positions. Denoising not only clarifies the dynamic and heterogeneous nature of spillover channels, but also sharpens the alignment between observed spillover patterns and known financial events. These findings highlight the necessity of denoising in spillover analysis for effective monitoring of systemic risk and market interconnectedness.

Complexity vs Empirical Score

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

Why this score: The paper presents a solid integration of neural network-based matrix denoising into the standard Diebold-Yilmaz VAR spillover framework. It offers good empirical coverage across global asset classes and clear exposition, though specific network architecture details and code availability could be further elaborated for maximum reproducibility.

Research Flowchart

  flowchart TD
    A[Research Goal: Measure Global Financial Spillovers by Denoising Signals] --> B[Data Inputs: Global Markets 2014-2025<br>Developed & Developing, Multiple Asset Classes]
    B --> C[Compute Initial Return & Volatility Covariance Matrices]
    C --> D[Neural Network-Based Denoising Architecture]
    D --> E[Estimate Static & Time-Varying Spillover Models]
    E --> F[Key Outcome: Developed Markets Shift from Transmitters<br>to Receivers During Systemic Stress e.g., COVID-19]
    E --> G[Key Outcome: Developing Markets Oscillate Roles;<br>Denoising Aligns Spillovers with Real Financial Events]

Cited References (13)

1. The index of general nonlinear D A E S (1995)
2. Clinical implications of dysregulated cytokine production (2000) — link
3. Quasimonotonicity, regularity and duality for nonlinear systems of partial differential equations (1995)
4. Algorithms for C omputer A lgebra (1992)
5. Software engineering—from auxiliary to key technologies (1992)
6. Conductive P olymers (1981)
7. Neuromuscular blocking drugs in man (1976)
8. Isolation and characterization of plasmid deoxyribonucleic acid from Streptomyces fradiae (1978)

0 of 13 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.