محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| التنسيق: | Recurso digital |
| اللغة: | |
| منشور في: |
Zenodo
2021
|
| الوصول للمادة أونلاين: | https://doi.org/10.5281/zenodo.14806341 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
جدول المحتويات:
- <p><span>Fraudulent claims in the insurance industry lead to billions of dollars in losses annually, adversely impacting insurers and policyholders through increased premiums and operational costs. With the advent of Artificial Intelligence (AI) and geospatial analytics, insurance carriers can now detect and mitigate fraud more effectively by analyzing location-based data and uncovering suspicious patterns. This paper explores how Guidewire and Duck Creek—two leading insurance software platforms—leverage real-time location tracking, AI-based pattern recognition, and geospatial intelligence to combat fraudulent claims. The study delves into the identification of staged accidents, fabricated policy claims, and suspicious location patterns, supported by real-world case studies illustrating the efficacy of these technologies.</span></p> <p><span>Comparative analysis highlights each platform’s fraud detection capabilities, focusing on machine learning models, geospatial intelligence tools, and anomaly detection methods. The research demonstrates how these platforms integrate satellite imagery, GIS data, and predictive analytics to identify fraudulent claims with higher accuracy while reducing false positives. Data visualization techniques such as heatmaps, risk scoring models, and spatial clustering are evaluated to underscore the role of AI in augmenting fraud detection workflows.</span></p> <p><span>The findings indicate that Guidewire’s predictive analytics framework often yields higher accuracy, while Duck Creek’s reconfigurability enables swift fraud case resolution via customizable AI models. The paper concludes with recommendations for next-generation fraud detection approaches, including integrating blockchain for immutable claim verification, deep learning for enhanced behavior analytics, and real-time IoT integration for proactive fraud monitoring.</span></p>