Risk Assessment Using Predictive Analytics

Abstract

Purpose: This research paper uses design science methodology to develop and evaluate a predictive analytics model for audit risk assessment. This research therefore contributes to improving the accuracy and efficiency of audit risk assessment through predictive analytics.   Theoretical framework: This study involved developing and evaluating a predictive analytics model for audit risk assessment, with it being tested during the audit of a publicly listed Saudi company.   Design/methodology/approach: This study adopted the design science research methodology, which is a problem-solving approach that involves the creation of innovative solutions to practical problems. This methodology is particularly relevant for developing and evaluating predictive analytics models for audit risk assessment, because it provides a structured, systematic approach to the problem-solving process. In the context of this research paper, the design science research methodology was used to develop and evaluate a predictive analytics model for audit risk assessment.   Findings: The proposed predictive analytics model for audit risk assessment was found to be an effective tool for helping auditors to make informed decisions based on data analysis. The model accurately identifies high-risk factors associated with an organization, provides valuable insights for decision-making, and highlights areas of potential risk that may require further investigation.   Research, practical & social implications: Future research could explore several areas related to predictive analytics in audit risk assessment. One important area to investigate would be the impact of using predictive analytics on audit quality. The ethical implications of using predictive analytics in audit risk assessment and the potential biases that could affect a model’s accuracy are also important areas to explore.   Originality/value: This paper helps improve our understanding of how predictive analytics can be effectively applied to audit risk assessment and how design science methodology can be used to develop and evaluate predictive analytics models. Furthermore, this study provides insights about the effectiveness of predictive analytics for improving audit risk assessment, thus contributing to the existing literature on the topic.