Florian Ruosch, Cristina Sarasua, Abraham Bernstein, DREAM: Deployment of Recombination and Ensembles in Argument Mining, In: 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, 2023-12-06. (Conference or Workshop Paper published in Proceedings)
Current approaches to Argument Mining (AM) tend to take a holistic or black-box view of the overall pipeline. This paper, in contrast, aims to provide a solution to achieve increased performance based on current components instead of independent all-new solutions. To that end, it presents the Deployment of Recombination and Ensemble methods for Argument Miners (DREAM) framework that allows for the (automated) combination of AM components. Using ensemble methods, DREAM combines sets of AM systems to improve accuracy for the four tasks in the AM pipeline. Furthermore, it leverages recombination by using different argument miners elements throughout the pipeline. Experiments with five systems previously included in a benchmark show that the systems combined with DREAM can outperform the previous best single systems in terms of accuracy measured by an AM benchmark. |
|
Jan von der Assen, Alberto Huertas Celdran, Janik Luechinger, Pedro Miguel Sánchez Sánchez, Gérôme Bovet, Gregorio Martínez Pérez, Burkhard Stiller, RansomAI: AI-powered Ransomware for Stealthy Encryption, In: IEEE Global Communications Conference, Institute of Electrical and Electronics Engineers, Kuala Lumpur, Malaysia, 2023-12. (Conference or Workshop Paper published in Proceedings)
Cybersecurity solutions have shown promising performance when detecting ransomware samples that use fixed algorithms and encryption rates. However, due to the current explosion of Artificial Intelligence (AI), sooner than later, ransomware (and malware in general) will incorporate AI techniques to intelligently and dynamically adapt its encryption behavior to be undetected. It might result in ineffective and obsolete cybersecurity solutions, but the literature lacks AI-powered ransomware to verify it. Thus, this work proposes RansomAI, a Reinforcement Learning-based framework that can be integrated into existing ransomware samples to adapt their encryption behavior and stay stealthy while encrypting files. RansomAI presents an agent that learns the best encryption algorithm, rate, and duration that minimizes its detection (using a reward mechanism and a fingerprinting intelligent detection system) while maximizing its damage function. The proposed framework was validated in a ransomware, Ransomware-PoC, that infected a Raspberry Pi 4, acting as a crowdsensor. A pool of experiments with Deep Q-Learning and Isolation Forest (deployed on the agent and detection system, respectively) has demonstrated that RansomAI evades the detection of Ransomware-PoC affecting the Raspberry Pi 4 in a few minutes with >90% accuracy. |
|
EvaCRC: Evaluating Code Review Comments, In: ESEC/FSE '23: 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, Association for Computing Machinery, 2023-12-03. (Conference or Workshop Paper published in Proceedings)
In code reviews, developers examine code changes authored by peers and provide feedback through comments. Despite the importance of these comments, no accepted approach currently exists for assessing their quality. Therefore, this study has two main objectives: (1) to devise a conceptual model for an explainable evaluation of review comment quality, and (2) to develop models for the automated evaluation of comments according to the conceptual model. To do so, we conduct mixed-method studies and propose a new approach: EvaCRC (Evaluating Code Review Comments). To achieve the first goal, we collect and synthesize quality attributes of review comments, by triangulating data from both authoritative documentation on code review standards and academic literature. We then validate these attributes using real-world instances. Finally, we establish mappings between quality attributes and grades by inquiring domain experts, thus defining our final explainable conceptual model. To achieve the second goal, EvaCRC leverages multi-label learning. To evaluate and refine EvaCRC, we conduct an industrial case study with a global ICT enterprise. The results indicate that EvaCRC can effectively evaluate review comments while offering reasons for the grades. |
|
Jakub Lokoč, Stelios Andreadis, Werner Bailer, Aaron Duane, Cathal Gurrin, Zhixin Ma, Nicola Messina, Thao-Nhu Nguyen, Ladislav Peška, Luca Rossetto, Loris Sauter, Konstantin Schall, Klaus Schoeffmann, Omar Shahbaz Khan, Florian Spiess, Lucia Vadicamo, Stefanos Vrochidis, Interactive video retrieval in the age of effective joint embedding deep models: lessons from the 11th VBS, Multimedia Systems, Vol. 29 (6), 2023. (Journal Article)
This paper presents findings of the eleventh Video Browser Showdown competition, where sixteen teams competed in known-item and ad-hoc search tasks. Many of the teams utilized state-of-the-art video retrieval approaches that demonstrated high effectiveness in challenging search scenarios. In this paper, a broad survey of all utilized approaches is presented in connection with an analysis of the performance of participating teams. Specifically, both high-level performance indicators are presented with overall statistics as well as in-depth analysis of the performance of selected tools implementing result set logging. The analysis reveals evidence that the CLIP model represents a versatile tool for cross-modal video retrieval when combined with interactive search capabilities. Furthermore, the analysis investigates the effect of different users and text query properties on the performance in search tasks. Last but not least, lessons learned from search task preparation are presented, and a new direction for ad-hoc search based tasks at Video Browser Showdown is introduced. |
|
Tobias Schlegel, Uschi Backes-Gellner, The role of fields of study for the effects of higher education institutions on regional firm location, Small Business Economics, Vol. 61 (4), 2023. (Journal Article)
The literature on knowledge spillovers provides evidence that higher education institutions (HEIs) positively affect regional firm location (i.e., start-ups or firms located in a region). However, less is known about how HEIs in different fields of study impact regional firm location in different industries. To investigate this question, we exploit the establishment of universities of applied sciences (UASs)—bachelor’s degree-granting three-year HEIs in Switzerland. We find that the effects of UASs are heterogeneous across fields of study and industries. UASs specializing in “chemistry and the life sciences” and “business, management, and services” are the only UASs that positively affect regional firm location across several industries. Positive effects emerge in service industries characterized by radical service, incremental product, or process innovations. Thus, UASs are not a one-size-fits-all solution for increasing regional firm location. Instead, only UASs specializing in particular fields of study positively influence firm location in certain industries. |
|
Markus Leippold, Hanlin Yang, Mixed-Frequency Predictive Regressions, Journal of Forecasting, Vol. 42 (8), 2023. (Journal Article)
We explore the performance of mixed-frequency predictive regressions for stock returns from the perspective of a Bayesian investor. We develop a constrained parameter learning approach for sequential estimation allowing for belief revisions. Empirically, we find that mixed-frequency models improve predictability, not only because of the combination of predictors with different frequencies but also due to the preservation of high-frequency features such as time-varying volatility. Temporally aggregated models misspecify the evolution frequency of the volatility dynamics, resulting in poor volatility timing and worse portfolio performance than the mixed-frequency specification. These results highlight the importance of preserving the potential mixed-frequency nature of predictors and volatility in predictive regressions. |
|
Zacharias Sautner, Laurence Van Lent, Grigory Vilkov, Ruishen Zhang, Pricing climate change exposure, Management Science, Vol. 69 (12), 2023. (Journal Article)
We estimate the risk premium for firm-level climate change exposure among S&P 500 stocks and its time-series evolution between 2005 to 2020. Exposure reflects the attention paid by market participants in earnings calls to a firm’s climate-related risks and opportunities. When extracted from realized returns, the unconditional risk premium is insignificant but exhibits a period with a positive risk premium before the financial crisis and a steady increase thereafter. Forward-looking expected return proxies deliver an unconditionally positive risk premium with maximum values of 0.5%–1% p.a., depending on the proxy, between 2011 and 2014. The risk premium has been lower since 2015, especially when the expected return proxy explicitly accounts for the higher opportunities and lower crash risks that characterize high-exposure stocks. This finding arises as the priced part of the risk premium primarily originates from uncertainty about climate-related upside opportunities. In the time series, the risk premium is negatively associated with green innovation; Big Three holdings; and environmental, social, and governance fund flows and positively associated with climate change adaptation programs. |
|
Fabienne Jedelhauser, Raphael Flepp, Egon Franck, Overshadowed by Popularity: The Value of Second-Tier Stars in European Football, Journal of Sports Economics, Vol. 24 (8), 2023. (Journal Article)
While second-tier stars lack popularity compared to superstars, their marginal contribution to team performance on the pitch relative to that of superstars is unknown. Relying on league-specific preseason market value distributions to define superstars and second-tier stars, we compare the marginal contributions of superstars and second-tier stars to team performance on the pitch in the top five European football leagues. Examining the impact of unexpected injury-related absences, we find that second-tier stars’ marginal contribution is at least equal to that of superstars. Thus, the players with arguably the highest costs for clubs do not contribute accordingly to short-run sportive success. |
|
Pascal Flurin Meier, Raphael Flepp, Egon Franck, Replication: Do coaches stick with what barely worked? Evidence of outcome bias in sports, Journal of Economic Psychology, Vol. 99, 2023. (Journal Article)
We replicate the finding of Lefgren et al. (2015) showing that professional basketball coaches in the NBA discontinuously change their starting lineup more often after narrow losses than after narrow wins. This result is consistent with outcome bias because such narrow outcomes are conditionally uninformative. As our paper shows, this pattern is not restricted to the NBA; we also find evidence of outcome bias in the top women’s professional basketball league and college basketball. Finally, we show that outcome bias in coaching decisions generalizes to the National Football League (NFL). We conclude that outcome bias is credible and robust, although it has weakened over time in some instances. |
|
Francesco D’Ercole, Alexander Wagner, The green energy transition and the 2023 Banking Crisis, Finance Research Letters, Vol. 58, 2023. (Journal Article)
This study examines the stock price reactions of environmentally responsible stocks during the onset of the 2023 banking crisis, triggered by the collapse of Silicon Valley Bank (SVB). Our findings indicate that stocks poised to benefit from the shift to a low-carbon economy underperformed during the 2023 crisis. This suggests that investors anticipate a slowdown in climate tech development due to distress in the banking sector. Our results underscore the significance of considering not only the influence of the climate crisis on financial stability, but also the pivotal role that financial stability plays in ensuring a successful energy transition. |
|
Berenika Sztandera, Klaudia Ponikiewska, Jan Cieciuch, Predictive validity of two conceptualizations of basic temperament dimensions, Personality and Individual Differences, Vol. 215, 2023. (Journal Article)
In this paper, we aimed to compare the predictive validity of two models of temperament structure: the one proposed within Strelau's Regulative Theory of Temperament (RTT) and the other developed by Strus, Ponikiewska and Cieciuch as a reconceptualization of the RTT fundamental temperament dimensions based on the insights from the temperamental Big Two and the Circumplex of Personality Metatraits. Specifically, we compared the predictive validity of these two temperament models in relation to a set of external variables related to stress (well-being, stress, PTSD, and COVID stress). The study was conducted on a Polish sample (N = 336, age range 17–65). We found that the reconceptualized temperament dimensions allow for better predictions of well-being, stress, and PTSD than the RTT ones. |
|
Ralph De Haas, Liping Lu, Steven Ongena, Close competitors? Bilateral bank competition and spatial variation in firms’ access to credit, Journal of Economic Geography, Vol. 23 (6), 2023. (Journal Article)
We interviewed 379 bank CEOs in 20 emerging markets to identify their banks’ main competitors. We show that banks are more likely to identify another bank as a main competitor in small-business lending when both banks are foreign owned or relationship oriented; when there exists a large spatial overlap in their branch networks and when the potential competitor has fewer hierarchical layers. We then construct a novel bilateral competition measure at the locality level and assess how well it explains geographic variation in firms’ credit constraints. We show that intense bilateral bank competition tightens local credit constraints, especially for small firms, as competition may impede the formation of lending relationships. |
|
Steven Ongena, Florentina Paraschiv, Endre J Reite, Counteroffers and Price Discrimination in Mortgage Lending, Journal of Empirical Finance, Vol. 74, 2023. (Journal Article)
This study analyzes price discrimination and household switching in the residential mortgage market. Using a unique proprietary micro dataset from Norway, we examine the factors that influence a bank’s choice to counter an offer from a competing bank and the difference between the loan rate paid by current clients when receiving a competing offer from another bank and the concurrent best rate offered to new customers by the current bank. The estimates show that a bank employs internal information to decide how to counter a competing offer and that current clients pay approximately 20 basis points more than new customers. We surmise that new regulations and digitalization enhance transparency and can reduce the rate differential. However, introducing new banking products and changes in the timing of rate differentiation - from immediate upfront to gradually over time - may be used to maintain a constant rate differential. |
|
Thomas Puschmann, Dario Quattrocchi, Decreasing the impact of climate change in value chains by leveraging sustainable finance, Journal of Cleaner Production, Vol. 429, 2023. (Journal Article)
Scope 3 greenhouse gas (GHG) emissions are frequently the most relevant element of a company's total emissions since they account for more than eighty percent. However, they are difficult to calculate since many stakeholders in the value chain are involved and emission data are usually not shared among them. Sustainable finance could provide a link to this discussion by providing data, digital data infrastructures and evaluation instruments. However, the existing research today is either limited to analyzing the levels of scope 3 emissions or to calculating them based on different measurement methods. How to implement scope 3 emissions reporting by solving the data sharing challenge remains mainly unexplored. This paper aims to close this gap by developing an approach, which chooses sustainable finance as a connecting element that (1) combines different calculation methods, (2) integrates cross-value chain data from different stakeholders and (3) combines primary and secondary data in a single model. The approach was developed in a prototype that uses real world data from collaboration with the UN-convened Net-Zero Asset Owner Alliance to evaluate its applicability. The findings of the prototype indicate that a digital data infrastructure can improve the calculation of scope 3 GHG emissions by improving data availability, accessibility and reliability and at the same time shows that the calculations are only as good as the data, which fuels this calculation. With this, the paper contributes to the theoretical and practical discussion about scope 3 GHG emission data. |
|
Mingze Gao, Yunying Huang, Steven Ongena, Eliza Wu, Banking on knowledge: Technology expertise and loan costs, VoxEU, CEPR Policy Portal, London, https://cepr.org/voxeu/columns/banking-knowledge-technology-expertise-and-loan-costs, 2023-12-01. (Scientific Publication In Electronic Form)
High-tech innovative firms often face difficulties in obtaining bank loans due to technological uncertainties and information asymmetries. This is because banks traditionally specialise in specific industry domains to mitigate risks. This column uses comprehensive patent data and syndicated bank loan data to show that banks also acquire technological expertise that extends beyond industry lines. This expertise is robustly related to lower loan spreads, and benefits both banks and future borrowers. Fostering collaboration between banks and innovative firms can boost productivity and can ultimately benefit both the economy and society. |
|
Shuo Liu, Nick Netzer, Happy times: measuring happiness using response times, American Economic Review, Vol. 113 (12), 2023. (Journal Article)
Surveys measuring happiness or preferences generate discrete ordinal data. Ordered response models, which are used to analyze such data, suffer from an identification problem. Their conclusions depend on distributional assumptions about a latent variable. We propose using response times to solve that problem. Response times contain information about the distribution of the latent variable through a chronometric effect. Using an online survey experiment, we verify the chronometric effect. We then provide theoretical conditions for testing conventional distributional assumptions. These assumptions are rejected in some cases, but overall our evidence is consistent with the qualitative validity of the conventional models. |
|
Clara Colombatto, Jim A C Everett, Julien Senn, Michel Maréchal, M J Crockett, Vaccine nationalism counterintuitively erodes public trust in leaders, Psychological Science, Vol. 34 (12), 2023. (Journal Article)
Global access to resources like vaccines is key for containing the spread of infectious diseases. However, wealthy countries often pursue nationalistic policies, stockpiling doses rather than redistributing them globally. One possible motivation behind vaccine nationalism is a belief among policymakers that citizens will mistrust leaders who prioritize global needs over domestic protection. In seven experiments (total N = 4,215 adults), we demonstrate that such concerns are misplaced: Nationally representative samples across multiple countries with large vaccine surpluses (Australia, Canada, United Kingdom, and United States) trusted redistributive leaders more than nationalistic leaders—even the more nationalistic participants. This preference generalized across different diseases and manifested in both self-reported and behavioral measures of trust. Professional civil servants, however, had the opposite intuition and predicted higher trust in nationalistic leaders, and a nonexpert sample also failed to predict higher trust in redistributive leaders. We discuss how policymakers’ inaccurate intuitions might originate from overestimating others’ self-interest. |
|
Paul Carrillo, Dave Donaldson, Dina Pomeranz, Monica Singhal, Ghosting the tax authority: fake firms and tax fraud in Ecuador, American Economic Review: Insights, Vol. 5 (4), 2023. (Journal Article)
An important but poorly understood form of firm tax evasion arises from “ghost firms” - fake firms that issue fraudulent receipts so that their clients can claim false deductions. We provide a unique window into this global phenomenon using transaction-level tax data from Ecuador. Five percent of firms use ghost invoices annually. Among these firms, ghost transactions comprise 14 percent of purchases. Ghost transactions are prevalent among large firms and firms with high-income owners and exhibit suspicious patterns, such as bunching below financial system thresholds. An innovative enforcement intervention targeting ghost clients rather than ghosts themselves led to substantial tax recovery. |
|
Angel Luis Perales Gómez, Lorenzo Fernández Maimó, Alberto Huertas Celdran, Félix J García Clemente, VAASI: Crafting valid and abnormal adversarial samples for anomaly detection systems in industrial scenarios, Journal of Information Security and Applications, Vol. 79, 2023. (Journal Article)
In the realm of industrial anomaly detection, machine and deep learning models face a critical vulnerability to adversarial attacks. In this context, existing attack methodologies primarily target continuous features, often in the context of images, making them unsuitable for the categorical or discrete features prevalent in industrial systems. To fortify the cybersecurity of industrial environments, this paper introduces a groundbreaking adversarial attack approach tailored to the unique demands of these settings. Our novel technique enables the creation of targeted adversarial samples that are valid within the framework of supervised cyberattack detection models in industrial scenarios, preserving the consistency of discrete values and correcting cases where an adversarial sample transitions into a normal one. Our approach leverages the SHAP interpretability method to identify the most salient features for each sample. Subsequently, the Projected Gradient Descent technique is employed to perturb continuous features, ensuring adversarial sample generation. To handle categorical features for a specific adversarial sample, our method scrutinizes the closest sample within the normal training dataset and replicates its categorical feature values. Additionally, Decision Trees trained within a Random Forest are utilized to ensure that the resulting adversarial samples maintain the essential abnormal behavior required for detection. The validation of our proposal was conducted using the WADI dataset obtained from a water distribution plant, providing a realistic industrial context. During validation, we assessed the mean error and the total number of adversarial samples generated by our approach, comparing it with the original Projected Gradient Descent method and the Carlini & Wagner attack across various parameter configurations. Remarkably, our proposal consistently achieved the best trade-off between mean error and the number of generated adversarial samples, showcasing its superiority in safeguarding industrial systems. |
|
José M Jorquera Valero, Pedro M Sánchez Sánchez, Manuel Gil Pérez, Alberto Huertas Celdran, Gregorio Martínez Pérez, Cutting-Edge Assets for Trust in 5G and Beyond: Requirements, State-of-the-Art, Trends & Challenges, ACM Computing Surveys, Vol. 55 (11), 2023. (Journal Article)
In 5G and beyond, the figure of cross-operator/domain connections and relationships grows exponentially among stakeholders, resources, and services, being reputation-based trust models one of the capital technologies leveraged for trustworthy decision-making. This work studies novel 5G assets on which trust can be used to overcome unsuitable decision-making and address current requirements. First, it introduces a background and general architecture of reputation-based trust models. Afterward, it analyzes pivotal 5G assets on which trust can enhance their performance. Besides, this article performs a comprehensive review of the current reputation models applied to 5G assets and compares their properties, features, techniques, and results. Finally, it provides current trends and future challenges to conducting forthcoming research in the area. |
|