Extensive research has been done on the analytical and empirical examination of financial data in annual reports to detect fraud; however, there is scant research on the analysis of text in annual reports to detect fraud. The basic premise of this research is that there are clues hidden in the text that can be detected to determine the likelihood of fraud. In this research, we examine both the verbal content and the presentation style of the qualitative portion of the annual reports using natural language processing tools and explore linguistic features that distinguish fraudulent annual reports from nonfraudulent annual reports. Our results indicate that employment of linguistic features is an effective means for detecting fraud. We were able to improve the prediction accuracy of our fraud detection model from initial baseline results of 56.75 percent accuracy, using a “bag of words” approach, to 89.51 percent accuracy when we incorporated linguistically motivated features inspired by our informed reasoning and domain knowledge.
Many governmental agencies and businesses organizations use networked systems to provide a number of services. Such a service-oriented network can be implemented as an overlay on top of the physical network. It is well recognized that the performance of many of the networked computer systems is severely degraded under node and edge failures. The focus of our work is on the resilience of service-oriented networks. We develop a graph theoretic model for service-oriented networks. Using this model, we propose metrics that quantify the resilience of such networks under node and edge failures. These metrics are based on the topological structure of the network and the manner in which services are distributed over the network. Based on this framework, we address two types of problems. The first type involves the analysis of a given network to determine its resilience parameters. The second type involves the design of networks with a given degree of resilience. We present efficient algorithms for both types of problems. Our approach for solving analysis problems relies on known algorithms for computing minimum cuts in graphs. Our algorithms for the design problem are based on a careful analysis of the decomposition of the given graph into appropriate types of connected components.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.