Gregor Weiß
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Gregor Weiß has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
Simon Fritzsch
4 shared publications- Felix Irresberger
Durham University
3 shared publications Philipp Scharner
Wirtschaftswissenschaftliche Fakultät Universität Leipzig Leipzig Germany
3 shared publications- Daniel Ziggel
Quasol GmbH, Münster, Germany
2 shared publications Felix Irresberger
2 shared publicationsMarcus Scheffer
Technische Universität Dortmund, Otto-Hahn-Str. 6a, D-44227 Dortmund, Germany
2 shared publications
Latest Publications
- Open Access
- 9 May 2026
- Published by Elsevier in SSRN Electronic Journal
CyRISK - A Capital Shortfall Measure of Cyber Risk in the Financial System
We develop a market-based, forward-looking measure of cyber-related capital shortfall for the global banking system. The framework incorporates a tradable cybersecurity factor into a dynamic systemic risk model with time-varying exposures estimated via conditional betas. Applied to a broad panel of banks, the measure reveals that conventional market-only stress tests materially understate system-wide capital needs, with incremental cyber-related shortfalls amounting to roughly one quarter of conventional shortfalls at their peak. A small set of globally active banks accounts for the bulk of marginal cyber risk exposure, identifying a dimension of systemic importance that is largely orthogonal to size, leverage, and market beta.
- 9 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCyRISK - A Capital Shortfall Measure of Cyber Risk in the Financial System
We develop a market-based, forward-looking measure of cyber-related capital shortfall for the global banking system. The framework incorporates a tradable cybersecurity factor into a dynamic systemic risk model with time-varying exposures estimated via conditional betas. Applied to a broad panel of banks, the measure reveals that conventional market-only stress tests materially understate system-wide capital needs, with incremental cyber-related shortfalls amounting to roughly one quarter of conventional shortfalls at their peak. A small set of globally active banks accounts for the bulk of marginal cyber risk exposure, identifying a dimension of systemic importance that is largely orthogonal to size, leverage, and market beta.
- Open Access
- 11 April 2026
- Published by Springer Nature in Review of Derivatives Research
- Vol. 29 (1)
Predicting option prices from their price history via machine learning
We benchmark the performance of widely used long short-term memory (LSTM) models in predicting standardized implied volatility (IV) of equity options against a range of alternative time series models. We forecast option prices over the period 2018-2023 and find universal models that are trained on data pooled across all underlyings to perform the best. The highest forecasting accuracy is achieved by a bidirectional LSTM model with one hidden layer. This provides evidence outside the stock markets that using universal models with pooled data across underlyings to train neural networks significantly improves the forecasting accuracy for equity option prices. Once the machine learning model is trained, one can inexpensively use the trained models to predict option prices up to 7 years into the future.
- 11 April 2026
- Published by Springer Nature in Review of Derivatives Research
- Vol. 29 (1)
Open AccessPredicting option prices from their price history via machine learning
We benchmark the performance of widely used long short-term memory (LSTM) models in predicting standardized implied volatility (IV) of equity options against a range of alternative time series models. We forecast option prices over the period 2018-2023 and find universal models that are trained on data pooled across all underlyings to perform the best. The highest forecasting accuracy is achieved by a bidirectional LSTM model with one hidden layer. This provides evidence outside the stock markets that using universal models with pooled data across underlyings to train neural networks significantly improves the forecasting accuracy for equity option prices. Once the machine learning model is trained, one can inexpensively use the trained models to predict option prices up to 7 years into the future.
- Open Access
- 22 August 2024
- Published by Elsevier in Journal of Empirical Finance
- Vol. 78
The 2008 short-selling ban’s impact on tail risk
- 22 August 2024
- Published by Elsevier in Journal of Empirical Finance
- Vol. 78
Open AccessThe 2008 short-selling ban’s impact on tail risk
- Open Access
- 26 June 2024
- Published by Elsevier in Insurance: Mathematics and Economics
- Vol. 118, 95-103
Comparing and quantifying tail dependence
- 26 June 2024
- Published by Elsevier in Insurance: Mathematics and Economics
- Vol. 118, 95-103
Open AccessComparing and quantifying tail dependence
- Open Access
- 28 May 2024
- Published by Wiley in Journal of Risk and Insurance
- Vol. 91 (2) , 263-298
Insurers' climate change risk management quality and natural disasters
We perform a textual analysis of insurers' climate risk disclosures and construct a climate change risk management quality index. Our index captures to what extent insurers identify, manage, and adjust their business model to climate change risk. We find that natural disasters in an insurer's home state lead to an increase in climate change risk management quality. The effect of natural disasters in an insurer's geographic markets on climate change risk management seems to be less pronounced. Overall, these results are consistent with salience theories of choice.
- 28 May 2024
- Published by Wiley in Journal of Risk and Insurance
- Vol. 91 (2) , 263-298
Open AccessInsurers' climate change risk management quality and natural disasters
We perform a textual analysis of insurers' climate risk disclosures and construct a climate change risk management quality index. Our index captures to what extent insurers identify, manage, and adjust their business model to climate change risk. We find that natural disasters in an insurer's home state lead to an increase in climate change risk management quality. The effect of natural disasters in an insurer's geographic markets on climate change risk management seems to be less pronounced. Overall, these results are consistent with salience theories of choice.
- 16 November 2023
- Published by Springer Nature in Annals of Operations Research
- Vol. 333 (1) , 47-78
Bi-objective reliability based optimization: an application to investment analysis
- 16 November 2023
- Published by Springer Nature in Annals of Operations Research
- Vol. 333 (1) , 47-78
Bi-objective reliability based optimization: an application to investment analysis
- 9 November 2023
- Published by Elsevier in Journal of Banking & Finance
- Vol. 158
Marginals versus copulas: Which account for more model risk in multivariate risk forecasting?
- 9 November 2023
- Published by Elsevier in Journal of Banking & Finance
- Vol. 158
Marginals versus copulas: Which account for more model risk in multivariate risk forecasting?
- 17 June 2023
- Published by Elsevier in Economic Analysis and Policy
- Vol. 79, 525-539
Revisiting the insurance–growth nexus
- 17 June 2023
- Published by Elsevier in Economic Analysis and Policy
- Vol. 79, 525-539
Revisiting the insurance–growth nexus
- Open Access
- 1 July 2021
- Published by Wiley in Journal of Risk and Insurance
- Vol. 88 (3) , 529-567
Estimating the relation between digitalization and the market value of insurers
We analyze the relation between digitalization and the market value of US insurance companies. To create a text‐based measure that captures the extent to which insurers digitalize, we apply an unsupervised machine learning algorithm—Latent Dirichlet Allocation—to their annual reports. We show that an increase in digitalization is associated with an increase in market valuations in the insurance sector. In detail, capital market participants seem to reward digitalization efforts of an insurer in the form of higher absolute market capitalizations and market‐to‐book ratios. Additionally, we provide evidence that the positive relation between digitalization and market valuations is robust to sentiment in the annual reports and the choice of the reference document on digitalization, both being issues of particular importance in text‐based analyses.
- 1 July 2021
- Published by Wiley in Journal of Risk and Insurance
- Vol. 88 (3) , 529-567
Open AccessEstimating the relation between digitalization and the market value of insurers
We analyze the relation between digitalization and the market value of US insurance companies. To create a text‐based measure that captures the extent to which insurers digitalize, we apply an unsupervised machine learning algorithm—Latent Dirichlet Allocation—to their annual reports. We show that an increase in digitalization is associated with an increase in market valuations in the insurance sector. In detail, capital market participants seem to reward digitalization efforts of an insurer in the form of higher absolute market capitalizations and market‐to‐book ratios. Additionally, we provide evidence that the positive relation between digitalization and market valuations is robust to sentiment in the annual reports and the choice of the reference document on digitalization, both being issues of particular importance in text‐based analyses.
- 18 October 2019
- Published by Taylor & Francis in Quantitative Finance
- Vol. 20 (3) , 425-446
Extreme dependence in investor attention and stock returns – consequences for forecasting stock returns and measuring systemic risk
We characterize co-movements in investor attention by modeling multivariate internet search volume data. Using a variety of copula models that can capture both asymmetric and skewed dependence, we find empirical evidence of strong non-linear and asymmetric dependence in the attention investors give to companies. Modeling three years of daily stock returns and search volumes from Google Trends for 29 bank names, we find a striking similarity between the dependence structure inherent in stock returns and the dependence in the corresponding time series of search queries. We then document the existence of significant asymmetric and skewed tail dependence in the joint distribution of stock returns and investor attention. Finally, stock returns and internet search volumes appear to evolve concurrently in real time with neither one leading the other. Our findings have important implications, e.g. for the analysis of banks' interconnectedness based on equity data and the pricing of investor attention in the cross-section of stock returns.
- 18 October 2019
- Published by Taylor & Francis in Quantitative Finance
- Vol. 20 (3) , 425-446
Extreme dependence in investor attention and stock returns – consequences for forecasting stock returns and measuring systemic risk
We characterize co-movements in investor attention by modeling multivariate internet search volume data. Using a variety of copula models that can capture both asymmetric and skewed dependence, we find empirical evidence of strong non-linear and asymmetric dependence in the attention investors give to companies. Modeling three years of daily stock returns and search volumes from Google Trends for 29 bank names, we find a striking similarity between the dependence structure inherent in stock returns and the dependence in the corresponding time series of search queries. We then document the existence of significant asymmetric and skewed tail dependence in the joint distribution of stock returns and investor attention. Finally, stock returns and internet search volumes appear to evolve concurrently in real time with neither one leading the other. Our findings have important implications, e.g. for the analysis of banks' interconnectedness based on equity data and the pricing of investor attention in the cross-section of stock returns.