Paper: arXiv 2512.10606
Authors: Paolo Bartesaghi, Rosanna Grassi, Pierpaolo Uberti
Abstract
The global balance is a well-known indicator of the behavior of a signed network. Recent literature has introduced the concept of local balance as a measure of the contribution of a single node to the overall balance of the network. In the present research, we investigate the potential of using deviations of local balance from global balance as a criterion for selecting outperforming assets. The underlying idea is that, during financial crises, most assets in the investment universe behave similarly: losses are severe and widespread, and the global balance of the correlation-based signed network reaches its maximum value. Under such circumstances, standard diversification (mainly related to portfolio size) is unable to reduce risk or limit losses. Therefore, it may be useful to concentrate portfolio exposures on the few assets - if such assets exist-that behave differently from the rest of the market. We argue that these assets are those for which the local balance strongly departs from the global balance of the underlying signed network. The paper supports this hypothesis through an application using real financial data. The results, in both descriptive and predictive contexts, confirm the proposed intuition.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 6.0/10 (capped from 7.0: transaction costs not modelled; see penalty flags)
- Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 7.0)
Why this score: The paper applies advanced mathematical concepts like network theory, matrix exponentials, and eigenvalue analysis for a financial application, and it is empirically supported with real financial data and a multi-dataset rolling-window backtest, including sensitivity analysis and performance metrics.
Research Flowchart
flowchart TD
A["Research Goal<br>Identify assets that deviate from market consensus<br>during crises for improved diversification"] --> B["Data Input<br>Financial Correlation Networks<br>Signed correlation matrices"]
B --> C["Key Methodology<br>Compute Global Balance<br>Compute Node-Level Local Balance"]
C --> D["Core Analysis<br>Calculate Local-Global Balance Deviation"]
D --> E{"Filter"}
E -- "Assets with<br>Significant Deviation" --> F["Portfolio Selection<br>Concentrate on unique assets"]
E -- "Standard Assets" --> G["Outcome: Risk Limitation<br>Resilience during<br>market crashes"]
F --> G
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes an investment strategy that selects assets whose local balance deviates from a high global balance, concentrating allocations in those few assets.
Source sentence
The main idea proposed in this paper is to study deviations of local balance from global balance in a signed network to identify distinctive behaviors of specific nodes. This intuition is applied in a financial context by proposing an investment strategy that concentrates allocations in a few assets when two conditions
Assumes 6
- Rolling window length ΔT is at least the number of assets N to ensure the correlation matrix is full rank. data
Source sentence
The experiments are performed using a standard rolling-window setting, where the window length ∆T satisfies the condition ∆T ≥N. This assumption ensures that C is a full-rank matrix.
- The rolling window is shifted by a step of Δt = 10 days. execution
Source sentence
In the applications, the rolling window is shifted by a step of ∆t = 10 days.
- Only stocks that remained in the index throughout the reference period are included. data
Source sentence
The number N of stocks in each dataset is smaller than the nominal number of index constituents, as the analysis is restricted to stocks that remained in the index throughout the reference period.
- When the selection conditions are met, the portfolio is equally weighted among the selected assets; otherwise it is equally weighted across all N assets. execution
Source sentence
Since the specific allocation rule is not the focus of the present work, we invest in an equally weighted portfolio of the selected assets when the conditions are met, and in an equally weighted portfolio (1/N) otherwise.
Show 2 more
- High global balance corresponds to periods of financial crisis where most assets report losses. market
Source sentence
In contrast, when the global balance of a financial correlation signed network is high, all nodes (assets) tend to report losses.
- The analysis uses daily log returns as the input data. data
Source sentence
The datasets contain daily log returns from 05/01/2005 to 17/09/2020.
Data
2005-05 – 2020-09 · NIKKEI stocks · equities · daily
- DAX market-prices unknown
Source sentence
The indices considered are DAX (N = 18), ESX (N = 42), FTSE (N = 80), and NIKKEI (N = 199).
- ESX market-prices unknown
Source sentence
The indices considered are DAX (N = 18), ESX (N = 42), FTSE (N = 80), and NIKKEI (N = 199).
- FTSE market-prices unknown
Source sentence
The indices considered are DAX (N = 18), ESX (N = 42), FTSE (N = 80), and NIKKEI (N = 199).
- NIKKEI market-prices unknown
Source sentence
The indices considered are DAX (N = 18), ESX (N = 42), FTSE (N = 80), and NIKKEI (N = 199).
Costs
Not modeled
Finds 5
- The proposed portfolio outperforms the equally weighted 1/N portfolio across all datasets. performance
Source sentence
What clearly emerges is that the proposed portfolio outperforms the 1/N portfolio across all datasets.
- Higher final portfolio value does not come with higher volatility. performance
Source sentence
Moreover, the higher final value does not imply higher volatility for the improved strategy.
- Global balance is negatively correlated with average market return and Sharpe ratio, indicating it measures systemic risk. statistical
Source sentence
As shown in Table 2.1 for all four datasets, this relationship is negative. This indicates that the values of
- Selected stocks exhibit higher mean returns, comparable variance, thinner left tail, fatter right tail, and greater skewness than non‑selected stocks. statistical
Source sentence
Both the distributions and the box plots show that the distribution of the selected stocks is characterized by a higher mean, comparable variance, a thinner left tail, a fatter right tail, and greater skewness.
- Experiments confirm the effectiveness of the proposed strategy in outperforming the benchmark equally weighted portfolio in both descriptive and predictive contexts. performance
Source sentence
Experiments conducted on four datasets of real financial data confirm both the intuition and the effectiveness of the proposed investment strategy in outperforming the benchmark equally weighted portfolio, which approximates the market.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 47 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (38)
- Global balance and systemic risk in financial correlation networks — → 2407.14272
- Open problems in the spectral theory of signed graphs (2019) — link
- Spectral criterion for cycle balance in networks (1980)
- On the notion of balance of a signed graph. (1953)
- Structural balance: a generalization of Heider’s theory. (1956)
- Structural duality (1957)
- Signed graphs for portfolio analysis in risk management (2002)
- The market rank indicator to detect financial distress (2020) — link
and 30 more
- Proper measures of connectedness (2020) — link
- An empirical comparison of correlation-based systemic risk measures (2023) — link
- Walk-based measure of balance in signed networks: Detecting lack of balance in social networks (2014) — link
- Rethinking structural balance in signed social networks (2019) — link
- Community Detection for Correlation Matrices (2013) — link
- Spectral and network methods in the analysis of correlation matrices of stock returns (2007) — link
- Covariance, correlation matrix, and the multiscale community structure of networks (2010) — link
- On the network topology of variance decompositions: Measuring the connectedness of financial firms (2014) — link
- Econometric measures of connectedness and systemic risk in the finance and insurance sectors (2012)
- Hierarchical structure in financial markets (1999) — link
- Spreading and Structural Balance on Signed Networks (2024) — link
- Some limit theorems for the eigenvalues of a sample covariance matrix (1982) — link
- Signed graphs (1982) — link
- Local balance of signed networks: Definition and application to reveal historical events in international relations (2023) — link
- Mathematical modeling of local balance in signed networks and its applications to global international analysis (2024)
- Matrices in the Theory of Signed Simple Graphs (2013)
- Signed graphs in data sciences via communicability geometry (2024) — link
- Systemic Risk and Complex Networks in Modern Financial Systems (2025)
- Understanding risk spillover in multi-layer financial networks: The role of bank–firm connections (2025)
- Systemic Risk: a Network Approach (2020) — [link](https://ideas.repec.org/p/mse/wpsorb/2025.htmlEmpir Econ)
- Systemic risk in bank-firm multiplex networks (2020)
- Temporal networks and financial contagion (2024)
- Financial contagion (2000)
- DebtRank : Too central to fail? financial networks, the fed and systemic risk (2012)
- Pathways towards instability in financial networks (2017)
- Directed clustering coefficient as a measure of systemic risk in complex banking networks (2014)
- Interconnectedness, G-SIBs and network dynamics of global banking (2018)
- Quantification of systemic risk from overlapping portfolios in the financial system (2021)
- Signed network models for portfolio optimization — → 2510.05377
- Loss of structural balance in stock markets (2021)
2 of 38 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.