Process-Based Fraud (PBF) is fraud enabled by process deviations that occur in business processes. Several studies have proposed PBF detection methods; however, false decisions are still often made because of cases with low deviation. Low deviation is caused by ambiguity in determining fraud attribute values and low frequency of occurrence. This paper proposes a method of detecting PBF with low deviation in order to correctly detect fraudulent cases. Firstly, the fraudulence attributes are established, then a fuzzy approach is utilized to weigh the importance of the fraud attributes. Further, multi-attribute decision making (MADM) is employed to obtain a PBF rating according to attribute values and attribute importance weights. Finally, a decision is made whether the deviation is fraudulent or not, based on the PBF rating. Experimental validation showed that the accuracy and false discovery rate of the method were 0.98 and 0.17, respectively.
Product reviews are usually determined by sentiment of customers; however sentiment analysis based on aspects still need further research. A hotel commonly has five aspects, which are location, meal, service, comfort and cleanliness. This research proposes methods to determine review sentiment according to the hotel aspects. A hotel reviews are preprocessed into a term list. Firstly, Latent Dirichelet Allocation (LDA) determines the hidden topics of a term list; then Semantic Similarity categorizes the term list based on the topic resulted by Latent Dirichelet Allocation (LDA) into the five aspects of a hotel. Then in calculating similarity measurement, the term list is expanded by using the Term Frequency-Inverse Cluster Frequency (TF-ICF) method. Finally, a classification of customer sentiment (satisfied or dissatisfied) is conducted by using the combination of Word Embedding and Long-short Term Memory (LSTM). The results show that the proposed method can classify the reviews into the five hotel aspects. The highest aspect categorization performance is obtained by using LDA + TF-ICF 100% + Semantic Similarity which reaches 85%; the performance sentiment classification for the highest aspect-based sentiment analysis is obtained by using Word Embedding + LSTM which reaches 93%; and the comfort aspect receives more negative sentiments compared to the sentiments of other aspects. Also the results show that a sentiment is influenced by an aspect.
In the industrial era 5.0, product reviews are necessary for the sustainability of a company. Product reviews are a User Generated Content (UGC) feature which describes customer satisfaction. The researcher used five hotel aspects including location, meal, service, comfort, and cleanliness to measure customer satisfaction. Each product review was preprocessed into a term list document. In this context, we proposed the Probabilistic Latent Semantic Analysis (PLSA) method to produce a hidden topic. Semantic Similarity was used to classify topics into five hotel aspects. The Term Frequency-Inverse Corpus Frequency (TF-ICF) method was used for weighting each term list, which had been expanded from each cluster in the document. The researcher used Word embedding to obtain vector values in the deep learning method from Long Short-Term Memory (LSTM) for sentiment classification. The result showed that the combination of the PLSA + TF ICF 100% + Semantic Similarity method was superior are 0.840 in the fifth categorization of the hotel aspects; the Word Embedding + LSTM method outperformed the sentiment classification at value 0.946; the service aspect received positive sentiment value higher are 45.545 than the other aspects; the comfort aspect received negative sentiment value higher are 12.871 than the other aspects. Other results also showed that sentiment was affected by the aspects.
Process-based fraud (PBF) is fraud caused by deviation from a business process model. Some studies have proposed methods for PBF detection; however, these are still not able to fully detect the occurrence of fraud. In this context, we propose a new method of PBF detection which carries out the behavior of the originators (users who perform events) to adjust the levels of fraud occured in the events. In this research, we propose a method of PBF detection with behavior model in order to increase accuracy. This is done firstly by analyzing the business processes that correspond to those in the standard operating system (SOP). Secondly, by calculating the event execution performed by the originator and his/her relations within the organization, whose behavior is then analyzed. Thirdly, by using the number of deviations and the originator behavior to calculate the attribute value. By using attribute importance weights, an attribute rating of each originator is kept. Finally, Multi Attribute Decision Making is used to decide the PBF rating of a case, on the basis of which it is decided whether fraud occurred or not. The experimental results show that this behavior model is able to reduce false positive and false negative, therefore, the method can increase the accuracy level by 0.01.
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.