Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
2 results
Search Results
Item Restricted Predicting Client Default Payments Using Machine Learning in Production Environment(Saudi Digital Library, 2025) Alanazi, Reem; LavendiniThis project investigates the application of machine learning techniques to predict client default payments in a credit card setting. Using a dataset of 30,000 Taiwanese clients, the study addresses the challenges of class imbalance, predictive accuracy, and fairness in credit risk assessment. An XGBoost model was developed and enhanced through feature engineering, resampling techniques (SMOTE/ADASYN), and class weighting to improve recall for defaulters while maintaining overall accuracy. Interpretability was achieved using SHAP values, providing transparency into model decisions. To mitigate demographic disparities, particularly across education levels, a fairness-constrained Random Forest was integrated into a two-stage cascade framework, reducing false positives while preserving high recall. The final cascade model achieved 84% accuracy, with 93% recall for non-defaulters and 53% recall for defaulters, significantly outperforming baseline benchmarks. Fairness audits revealed that education-based disparities could be reduced with minimal performance trade-offs, while age-based fairness was largely maintained. The project demonstrates a practical, interpretable, and ethically aware pipeline for credit default prediction, with deployment considerations and directions for future research in cost-sensitive learning, advanced fairness constraints, and real-time monitoring35 0Item Restricted The Use of Artificial Intelligence and Machine Learning in Zero Trust Networks(Newcastle University, 2024) Alnadhari, Sultan Majid; Shepherd, CarltonThis paper focuses on the application of Artificial Intelligence (AI) and Machine Learning (ML) within the context of the Zero Trust (ZT) security model to improve Cybersecurity within the ever-evolving digital landscape. Conventional security models that focus on proactively protecting the perimeter and assuming trust within internal networks are often inadequate against these threats. Zero trust can be characterised as a modern approach resulting from the "never trust, always verify" principle; thus, it implies an unceasing process of the users' authentication and access authorisation. Regarding Zero Trust security, this research builds upon the concept by incorporating AI/ML techniques to enhance threat, anomaly, and predictive detection. The first and foremost is the implementation of deep learning models using an optimised Keras framework better suited for the unique dynamics of the Zero Trust environments. Some of these models successfully differentiate and filter network traffic into normal and malicious categories using state-of-the-art features like dropout characters and dense layers. Briefly discuss some problems and solutions, for instance, data shift and model performance decline in conditions that change with time: transfer learning and periodically, for example, perform retraining of the model. Real-world assessments clearly show that incorporating Artificial Intelligence and Machine Learning into the Zero Trust Architectures enhances the capability to identify and mitigate advanced persistent threats and zero-day attacks. Therefore, this research will form a basis for more work in the area of Artificial Intelligence and Cybersecurity by presenting the knowledge required to establish intelligent security systems that can learn to handle new threats as they emerge effectively in real-time. Specifically, the results highlight how these speeds strengthen Zero Trust security solutions against emerging threats.57 0