Dynamic large financial networks via conditional expected shortfalls

Abstract

In this article, we first generalize the Conditional Auto-Regressive Expected Shortfall (CARES) model by introducing the loss exceedances of all (other) listed companies in the Expected Shortfall related to each firm, thus proposing the CARES-X model (where the 'X', as usual, stands for eXtended in the case of large-dimensional problems). Second, we construct a regularized network of US financial companies by introducing the Least Absolute Shrinkage and Selection Operator in the estimation step. Third, we also propose a calibration approach for uncovering the relevant edges between the network nodes, finding that the estimated network structure dynamically evolves through different market risk regimes. We ultimately show that knowledge of the extreme risk network links provides useful information, since the intensity of these links has strong implications on portfolio risk. Indeed, it allows us to design effective risk management mitigation allocation strategies.

Green finance: Evidence from large portfolios and networks during financial crises and recessions

“…This evidence is consistent with the findings discussed by Bonaccolto et al (2021) and is clear in Figure 9, where we plot the network density calculated from the 646 rolling sub‐samples. The network density ranges from a minimum value of 0.1483 (376‐th sub‐sample) to a maximum value of 0.1957 (124‐th sub‐sample).…”

“…Specifically, our dataset includes the weekly returns yielded by these firms from January 12, 2007, to March 31, 2023 (i.e., 846 weeks). Following Bonaccolto and Paterlini (2020) and Bonaccolto et al (2021), we use a weekly horizon, as it better reflects the rebalancing activity of fund managers, while a daily frequency is typically considered as a short time interval.…”

Systemic risk and severe economic downturns: A targeted and sparse analysis

“…Among possible future extensions of this work, we mention first the application of our methodology to other datasets, which would allow us to assess the differences across markets in response to some crises (Engle et al, 2015;Dungey et al, 2020). Second, extending the analysis to non-market value systemic risk measures as well as to other indicators tracking additional systemic dimensions would also be of interest; as examples, one might consider other illiquidity measures (Belkhir et al, 2020) or interconnectedness measures (Giudici et al, 2020;Bonaccolto et al, 2021).…”

Mean–variance efficient large portfolios: a simple machine learning heuristic technique based on the two-fund separation theorem

“…provides benefits in terms of the sparsity of the portfolio (indirectly associated with diversification/concentration, positive weights and turnover) and elaborates on the properties of optimal portfolios in various market conditions (e.g., Brodie et al, 2009;DeMiguel et al, 2009a;Fan et al, 2012;Yen and Yen, 2014;Fastrich et al, 2015;Bonaccolto et al, 2018;Bonaccolto and Paterlini, 2020;Bonaccolto et al, 2021). In this article, we show that the Two-Fund Separation Theorem approximately holds when supplementary realistic constraints are considered in the one-period Markowitz' (1952) seminal setting.…”