Revenue assurance and the issuance of Financial Fraud alerts are essential challenges that impact both financial institutions and businesses. This is a complex problem where new challenges and methods consistently arise, necessitating the continuous improvement of detection systems. In this context, the use of various computational intelligence techniques and elements from neutrosophic theory can assist in managing uncertainty and indeterminacy. The methods section includes a brief analysis of the state of the art in artificial intelligence for detecting financial fraud situations. Furthermore, an algorithm is proposed for detecting potential financial fraud situations, supported by data linguistic summarization techniques. These techniques are employed in combination with principles from neutrosophic theory. Subsequently, in the results section, the proposal is validated by comparing the proposed method with a rule-based approach reported in the literature. Additionally, the model is evaluated by subject matter experts, demonstrating the contributions of the proposed model.