Benjamin ClaphamMicha BenderJens LausenPeter Gomber...
1463-1514页
查看更多>>摘要：Abstract Regulators conduct regulatory impact analyses (RIA) to evaluate whether regulatory actions fulfill the desired goals. Although there are different frameworks for conducting RIA, they are only applicable to regulations whose impact can be measured with structured data. Yet, a significant and increasing number of regulations require firms to comply by specifying and communicating textual data to consumers and supervisors. Therefore, we develop a methodological framework for RIA in case of unstructured data following the design science research paradigm. The framework enables the application of textual analysis and natural language processing to assess the impact of regulatory actions that result in unstructured data and offers guidance on how to map suitable methods to the dimensions impacted by the regulation. We evaluate the framework by applying it to the European financial market regulation MiFID II, specifically the recent regulatory changes regarding best execution. Thereby, we show that MiFID II failed to improve informativeness and comprehensibility of best execution policies.
查看更多>>摘要：Abstract Security token offerings (STOs) are a new means for ventures to raise funding, where digital tokens are issued as regulated investment products on the blockchain. We study market outcomes in the primary and secondary markets for security tokens and examine the associated determinants in the context of signaling theory. We analyze success determinants of 138 STOs and find that a pre-sale and the announcement of token transferability are positively related to the funding success and serve as positive quality signals for investors to overcome information asymmetries. We examine 108 security tokens traded on centralized and decentralized exchanges related to the rapidly evolving area of decentralized finance. There is hardly any underpricing in the market, and it is positively associated with the crypto market sentiment as an external signal. When traded on the secondary market, security tokens generate both extremely positive and negative returns for various short-term time horizons. We disentangle the liquidity situation in the market between centralized and decentralized exchanges and find that decentralized marketplaces are less liquid and offer lower barriers to entry, indicating slow market completion.
查看更多>>摘要：Abstract Recent empirical evidence indicates that bond excess returns can be predicted using machine learning models. However, although the predictive power of machine learning models is intriguing, they typically lack transparency. This paper introduces the state-of-the-art explainable artificial intelligence technique SHapley Additive exPlanations (SHAP) to open the black box of these models. Our analysis identifies the key determinants that drive the predictions of bond excess returns produced by machine learning models and recognizes how these determinants relate to bond excess returns. This approach facilitates an economic interpretation of the predictions of bond excess returns made by machine learning models and contributes to a thorough understanding of the determinants of bond excess returns, which is critical for the decisions of market participants and the evaluation of economic theories.
查看更多>>摘要：Abstract This study investigates the predictive power of CEO characteristics on accounting fraud utilizing a machine learning approach. Grounded in upper echelons theory, we show the predictive value of widely neglected CEO characteristics for machine learning-based accounting fraud detection in isolation and as part of a novel combination with raw financial data items. We employ five machine learning models well-established in the accounting fraud literature. Diverging from prior studies, we introduce novel model-agnostic techniques to the accounting fraud literature, opening further the black box around the predictive power of individual accounting fraud predictors. Specifically, we assess CEO predictors concerning their feature importance, functional association, marginal predictive power, and feature interactions. We find the isolated CEO and combined CEO and financial data models to outperform a no-skill benchmark and isolated approaches by large margins. Nonlinear models such as Random Forest and Extreme Gradient Boosting predominantly outperform linear ones, suggesting a more complex relationship between CEO characteristics, financial data, and accounting fraud. Further, we find CEO Network Size and CEO Age to contribute second and third strongest towards the best model’s predictive power, closely followed by CEO Duality. Our results indicate U-shaped, L-shaped, and weak L-shaped associations for CEO Age, CEO Network Size, CEO Tenure, and accounting fraud, consistent with our superior nonlinear models. Lastly, our empirical evidence suggests that older CEOs who are not simultaneously serving as chairman and CEOs with an extensive network and high inventory are more likely to be associated with accounting fraud.
查看更多>>摘要：Abstract The main challenge in empirical asset pricing is forecasting the future value of assets traded in financial markets with a high level of accuracy. Because machine learning methods can model relationships between explanatory and dependent variables based on complex, non-linear, and/or non-parametric structures, it is not surprising that machine learning approaches have shown promising forecasting results and significantly outperform traditional regression methods. Corresponding results were achieved for CAT bond premia forecasts in the primary market. However, since secondary market data sets have a panel data structure, it is unclear whether the results of primary market studies can be applied to the secondary market. Against this background, this study aims to build the first out-of-sample forecasting model for CAT bond premia in the secondary market, comparing different modeling approaches. We apply random forest and neural networks as representatives of machine learning methods and linear regression based on a comprehensive data set of CAT bond issues and across various forecasting settings and show that random forest forecasts are significantly more precise. Because the lack of transparency of machine learning methods may limit their applicability, especially for institutional investors, we show ways to identify important variables in the context of random forest price forecasting.
Christian LohmannSteffen MöllenhoffThorsten Ohliger
1661-1690页
查看更多>>摘要：Abstract This study uses generalized additive models to identify and analyze nonlinear relationships between accounting-based and market-based independent variables and how these affect bankruptcy predictions. Specifically, it examines the independent variables that Altman (J Financ 23:589–609, 1968; Predicting financial distress of companies. Revisiting the Z-score and ZETA® models. Working paper, 2000) and Campbell et al. (J Financ 63:2899–2939, 2008) used and analyzes what specific form these nonlinear relationships take. Drawing on comprehensive data on listed U.S. companies, we show empirically that the bankruptcy prediction is influenced by statistically and economically relevant nonlinear relationships. Our results indicate that taking into account these nonlinear relationships improves significantly several statistical validity measures. We also use a validity measure that is based on the profitability of the bankruptcy prediction models in the context of credit scoring. The findings demonstrate that taking into account nonlinear relationships can substantially increase the discriminatory power of bankruptcy prediction models.
查看更多>>摘要：Abstract The tendency of humans to shy away from using algorithms—even when algorithms observably outperform their human counterpart—has been referred to as algorithm aversion. We conduct an experiment with young adults to test for algorithm aversion in financial decision making. Participants acting as investors can tie their incentives to either a human fund manager or an investment algorithm. We find no sign of algorithm aversion: participants care about returns, but do not have strong preferences which financial intermediary obtains these returns. Contrary to what has been suggested, participants are neither quicker to lose confidence in the algorithm after seeing it err. However, we find that participants’ inability to separate skill and luck when evaluating intermediaries slows down their migration to the algorithm.
NETL
NSTL