Zeeshan Ahmed

This study evaluates whether a deep-learning volatility model improves market-risk measurement relative to established econometric benchmarks. Using daily returns for twelve developed and emerging equity indices from January 2000 to September 2026—with the KSE-100 and IMOEX series taken from the Pakistan Stock Exchange and the Moscow Exchange respectively, because the public feeds for both are truncated—we estimate one-day value-at-risk (VaR) and conditional value-at-risk (CVaR) at the 95% and 99% levels using three approaches: unconditional historical simulation, a GARCH(1,1) model with Student-t innovations and filtered historical simulation (FHS), and a long short-term memory (LSTM) neural network. VaR and CVaR are reported as signed returns, with a negative number denoting a loss; the United States 99% VaR is −3.5% and the corresponding CVaR is −5.0%. Model adequacy is assessed with the Kupiec unconditional-coverage and Christoffersen conditional-coverage backtests—decomposed into their independence (LR_ind) and coverage (LR_uc) components—and volatility-forecast accuracy is compared out-of-sample using the QLIKE robust loss. Four findings emerge. First, static historical VaR attains correct average coverage yet fails the conditional-coverage test in eleven of twelve markets; the failure is driven almost entirely by the independence component, confirming that its exceedances cluster in high-volatility episodes rather than reflecting incorrect average coverage. Second, the GARCH-FHS model, which conditions the risk estimate on time-varying volatility, restores conditional coverage in all twelve markets, including on a backtest window matched exactly to the LSTM’s held-out test period, where it passes in eight of twelve markets against two of twelve for the LSTM. Third, the LSTM is correctly signed but poorly calibrated: with the plug-in FHS construction it jointly passes both backtests in only two of twelve markets, with breach rates well below the nominal 5% in most of the rest, a pattern consistent with a significant drift between the training-window and test-window standardised-residual distributions (Kolmogorov–Smirnov p < 0.05 in eight of twelve markets). Roughly half of that over-conservatism is attributable to the two-step plug-in design rather than to the network: retraining the same architecture directly on the tail quantiles with a composite pinball loss raises the mean breach rate from 2.8% to 4.3% against a nominal 5% but still yields joint coverage in only six of twelve markets, against eight of twelve for a window-matched GARCH-FHS. Fourth, a Diebold–Mariano test on the QLIKE loss finds GARCH significantly more accurate than the LSTM in ten of twelve markets at the 5% level and in nine of twelve after a Holm–Bonferroni correction for multiple testing; the LSTM is not significantly more accurate than GARCH in any market, before or after correction—nor in any of the 320 additional training runs reported below. These results are reported for a specific neural implementation, and we are deliberate about the scope of the claim they support: we do not find evidence that a single-layer LSTM trained with a Huber loss on the next-day absolute return and converted to VaR through a plug-in FHS residual distribution is competitive with GARCH(1,1)-t FHS in any of the twelve markets we study, under a randomised search over six training hyperparameters comprising 40 configurations in each of five markets and across ten random seeds per market in all twelve. The ranking is unchanged when the LSTM is instead trained directly on the quantile it is judged on with a composite pinball loss, when the Gaussian absolute-return conversion is replaced by its empirical counterpart, and when a Parkinson high–low range proxy replaces the squared return in the loss function. We do not claim, and our design cannot establish, that no neural architecture can beat GARCH for this task. The decisive gain in VaR adequacy comes from conditioning on dynamic volatility, and within the conditional-model class a parsimonious GARCH(1,1) is a demanding benchmark. We discuss implications for regulatory backtesting, tail-risk management, and the design of hybrid econometric-neural systems and report the full replication pipeline (data-download, modelling, and backtesting code) alongside this submission.

We compare three families of Value-at-Risk and expected shortfall estimators—rolling historical simulation, GARCH(1,1) filtered historical simulation (FHS), and a walk-forward multi-quantile LSTM—on identical, strictly out-of-sample footing across thirty-nine developed, emerging, and frontier equity markets over 2005–2025 (192,789 market-days). The answer to the title question is no. Historical simulation fails the Christoffersen independence test in every market. Filtering repairs most of this: FHS passes conditional coverage in nineteen markets, attains a 4.9% breach rate against a 5% target, and prices expected shortfall essentially without bias (mean Acerbi–Székely Z₂ of −0.003). The neural measure improves on historical simulation but passes conditional coverage in only four markets and understates tail severity by roughly 20% (Z₂ = −0.195); it tracks filtered more closely than historical VaR (within-market correlation 0.53 versus 0.40, p < 0.001), which indicates that much of the neural signal is volatility filtering in disguise. Quadrupling the network narrows this gap without closing it. In the macroeconomic panel, however, the neural family is the least procyclical: a one-point rise in GDP growth compresses historical tail risk by 4.3% but neural risk by only 1.5%. Machine learning tail-risk measures should therefore be benchmarked against filtered, not merely unconditional, classical methods and used alongside rather than instead of them.

The purpose of this research is to explore the role of women on board in defining the relationship of risk with performance of non-financial firms in Pakistan. The study uses the sample over the period 2014–2023. Moreover, the study employs GMM and results are robust to different estimation techniques like 2SLS, and DID approach. The study also explores the role of women on board between risk and firm performance based on earnings quality. The study has found that risk significantly declines the firm performance. However, the women in corporate board room strives to improve the firm performance. The gender diversity in board of directors minimizes the risk that helps to improve the firm performance. Therefore, the women on board strengthen the relationship between risk and firm performance. Furthermore, the results reveal that this relationship is more pronounced in firms with high earning quality in comparison with companies with low earnings quality.

Using a hand-collected sample of non-financial firms listed on the Pakistan Stock Exchange (PSX) over the period of 2011–2021, we examine the joint effect of intellectual capital and innovation on the financial vulnerability of a firm, which is an important risk factor that a firm may face in its operation. We first use the static fixed-effect panel model as our baseline regression model and find that the level of intellectual capital of a firm strengthens the positive effect of the adoption of product and market innovation on reducing the financial vulnerability of the firm. We also conduct additional analyses using alternative measures of financial vulnerability, as well as various regression models, and confirm that the results are robust under different scenarios. Overall, the results highlight the positive role of the intellectual capital, as well as the joint effect of intellectual capital and innovation, in mitigating the financial vulnerability faced by a firm and thus have academic and practical implications to academic researchers and practitioners.

Using a unique sample of 13,412 firm-year observations from 19 countries of the emerging economies for the period of 2011 to 2019, we investigate the association between the firms’ environmental, social, and governance (ESG) performance and their value creation in the product market. Specifically, we first used the pooled OLS regression model for panel data as our baseline model and found that ESG performance (as well as its pillars) has a strong positive effect on the future value creation of the firms in the product market. We also conducted some additional analyses using various regression models, as well as adopting multiple tests for endogeneity, and the additional analyses revealed that the results are robust under different scenarios. Overall, the findings of this study highlight the importance of firm-level ESG performance for the value creation of firms in the product market in emerging economies and have theoretical and practical implications for academic researchers, market participants, and government entities in studying, evaluating, and governing firms’ ESG performance and reporting.