Aug 2026· International Journal of Advanced Artificial Intelligence Research· 0 citations
TL;DR
Data quality, class imbalance, privacy preservation, model interpretability, scalability and regulatory compliance are among the key challenges that are critically analyzed.
Abstract
Insurance fraud is a big problem that the insurance industry is trying to solve. Economic loss, operational costs, and a decline in consumer trust are all consequences of insurance fraud. Traditional techniques of fraud detection, such as rule-based systems and human processes, frequently fail to detect more sophisticated fraud schemes. By analyzing complicated data in real-time, artificial intelligence (AI) has been shown to be an effective tool for automating the identification of fraud. Machine learning, explainable AI, federated learning, deep learning, reinforcement learning, natural language processing, and the most current approaches to AI methods in insurance fraud detection are included in this review. The paper also contains a discussion on traditional fraud detection methods, most popular insurance frauds, data preprocessing methods and some common metrics. Additionally, it looks at the latest research studies and points out the advantages and disadvantages of the available AI-driven approaches. Data quality, class imbalance, privacy preservation, model interpretability, scalability and regulatory compliance are among the key challenges that are critically analyzed.
The review highlights the transformative potential of AI while emphasizing the need for ethical, transparent, and secure implementation strategies to maximize effectiveness in combating increasingly sophisticated financial fraud schemes.
G. Onyarin· International journal of res...· 0 citations
It is concluded that AI is a critical component of modern financial security infrastructure and will play an increasingly important role in combating financial fraud.
E. Harris· International Journal of Com...· 0 citations
Insurance fraud is a major problem for insurers, especially in the vehicle insurance industry. It affects pricing tactics and causes financial losses. Class imbalance, when fraudulent claims are far less common than legitimate claims, frequently affects fraud detection models, and missing data makes the task even more difficult. Two vehicle insurance datasets—a conventional dataset and an Egyptian real-life dataset—are used in this study to address these problems. In order to improve the accuracy and prediction potential of the model, the AdaBoost Classifier is incorporated into the suggested methodology, which also addresses missing data and class imbalance. The findings show that correcting class imbalance is essential to enhancing model performance, and handling missing data also helps to produce predictions that are more trustworthy. By increasing prediction accuracy and decreasing overfitting, which is frequently a problem in fraud detection models, the AdaBoost Classifier greatly outperforms current methods. This study offers insightful information about how enhancing data quality and utilising cutting-edge algorithms like AdaBoost can improve fraud detection systems, ultimately resulting in more successful identification of fraudulent claims. These improvements can greatly help insurance businesses make better decisions, lower financial losses, and improve pricing strategies.
Uzma Fatima, Lubna Nausheen, Sadaf Jahan· International Journal of AI...· 0 citations
Insurance claim fraud continues to pose substantial financial and operational challenges for insurance companies worldwide, particularly in auto insurance, where fraudulent cases form a small but highly impactful portion of overall claims. One of the significant technical difficulties in detecting such fraud is the severe class imbalance in real-world insurance datasets, where legitimate claims vastly outnumber fraudulent ones. This study presents a systematic performance evaluation of classical machine learning (ML) classification models for insurance fraud detection under conditions of extreme class imbalance. The proposed framework focuses on widely used supervised learning algorithms, including Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF), with an emphasis on understanding their behavior when trained on imbalanced data. To mitigate class imbalance bias, the Synthetic Minority Oversampling Technique (SMOTE) is applied to the dataset before model training. Model performance is evaluated using multiple metrics such as accuracy, precision, recall, and F1-score, which provide a more reliable assessment than accuracy alone in fraud detection scenarios. Experimental results demonstrate that ensemble-based methods, particularly Random Forest, achieve superior performance in identifying minority class fraud cases while maintaining stable overall classification accuracy. This research provides practical insights into selecting suitable classical ML models for insurance fraud detection, supporting the development of reliable decision support systems for insurance providers operating with imbalanced data.
Garima Sharma· International Journal For Mu...· 0 citations
Financial fraud is a growing concern for the global economy, with hundreds of billions of dollars lost every year, and the traditional rule-based fraud detection systems are no longer effective because they are unable to cope with the increasing complexity of fraud schemes. In this paper, we propose FraudShield-XAI, an ensemble learning framework to produce high fraud detection performance and transparent/interpretable decision making, which uses a stacking-based framework consisting of XGBoost, random forests, and an adaptive neural network meta-learner. We evaluate and train the framework using two widely used datasets, the IEEE-CIS Fraud Detection dataset and the PaySim simulated mobile money transactions dataset, and in order to address the class imbalance issue that is typical in fraud detection problems, we apply the Synthetic Minority Oversampling Technique with Edited Nearest Neighbours (SMOTE-ENN). Our experimental results show that FraudShield-XAI outperforms traditional single-model based approaches with an AUC-ROC of 98.72%, an MCC of 0.923, and an F1-score of 97.84%, and we use SHAP and LIME to explain the predictions of FraudShield-XAI, providing the most influential features for each prediction. Identified key factors include transaction velocity, merchant category, and geographical deviations, which can offer actionable insights to compliance teams and fraud analysts, therefore, FraudShield-XAI bridges the performance vs. interpretability gap, which is essential for regulatory approval and real-world deployment in fintech settings.
Soltand Albasha Albasha· Al-Noor Journal of Engineeri...· 0 citations
This study reviews the development and application of artificial intelligence (AI) and big data analytics (BDA) for fraud detection in accounting and auditing. The review adopts a systematic literature review approach guided by PRISMA principles and synthesizes 20 peer-reviewed and scholarly sources covering data mining, machine learning, natural language processing, deep learning, audit analytics, and big data. The literature indicates that AI and BDA extend fraud detection from periodic, sample-based procedures toward continuous, risk-oriented analysis of large volumes of structured and unstructured data. Machine learning methods, including logistic regression, support vector machines, decision trees, ensemble methods, neural networks, and deep learning, are increasingly used to classify suspicious observations and identify nonlinear fraud patterns. BDA strengthens these models by integrating financial ratios, transaction records, audit evidence, textual disclosures, management commentary, and external information. The review also identifies persistent challenges involving class imbalance, data quality, explainability, privacy, model bias, cybersecurity, and auditor competencies. Overall, the evidence suggests that AI and BDA are most effective when deployed as decision-support mechanisms that complement professional skepticism and audit judgment rather than replace them. Future research should emphasize multimodal data integration, explainable AI, real-time analytics, robust validation across jurisdictions, and governance frameworks for responsible AI-enabled accounting and auditing.
Rosiana Ramadhon, Emmarani Nuristya, Batista Sufa Kefi et al.· Journal of Creative Power a...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
