A General Framework for the Identification and Categorization of Risks - An Application to the Context of Financial Markets

Risk represents a significant part of humans' interaction and has to be considered in various decision-making processes across diverse business and research areas. Furthermore, the disregard or non-awareness of certain risks may result in inappropriate decision-making processes and inadequate risk management practices which may negatively influence firms' performances. Thus, to the best of our knowledge, this paper is the first to develop an algorithmic-based and generally applicable framework that generates an extensive and integrated identification and categorization scheme of certain risks, using text mining and machine learning approaches. To demonstrate the applicability of our framework, we exemplarily apply our derived approach to the context of financial markets. Hence, we identify 193 financial market risks and categorize them into five categories by using common machine learning techniques. To evaluate the general applicability, we additionally apply the derived framework to the context of information systems. Finally, we give strong indications regarding robustness and superiority of our derived framework by benchmarking it against more manual risk identification techniques and other clustering approaches