Healthcare insurance fraud has become a major problem worldwide in recent decades, resulting in significant financial losses for every affected country. However, traditional fraud detection methods tend to focus on analyzing data from the current period and overlook historical information. In this study, we propose a novel approach inspired by the financial concept of ‘credit’ to detect fraudulent activities in various domains, such as healthcare insurance, credit card, and online retail transactions.Our approach aims to build a credit evaluation model that can differentiate between fraudulent and normal activities based on their historical records. We acknowledge that many fraud detection methods have been proposed, but they often struggle to detect edge cases, which limits their practical applicability. To overcome this challenge, we propose the Credit Evaluation Model (CEM), which uses a Time Interval-Aware Long Short-Term Memory (LSTM) algorithm to assist fraud detection. Moreover, we propose a new approach that transforms traditional binary classification into a multi-classification problem, which improves the model's ability to handle diverse fraudulent activities.We conducted experiments to evaluate the effectiveness of our proposed approach and model, comparing them against baseline algorithms and recently proposed methods. The results show that our approach outperforms the others, demonstrating its potential for practical use in detecting fraudulent activities in various domains.