Train-Test Split Strategies in Anomaly Detection Model Evaluation

Generative models have revolutionized multiple domains, yet their application to tabular data remains underexplored. Evaluating generative models for tabular data presents unique challenges due to structural complexity, large-scale variability, and mixed data types, making it difficult to intuitively capture intricate patterns. Existing evaluation metrics offer only partial insights, lacking a comprehensive measure of generative performance. To address this limitation, we propose three novel evaluation metrics: FAED, FPCAD, and RFIS. Our extensive experimental analysis, conducted on three stan

Research goal: What is the impact of different train-test split strategies on the AVPR and AUC metrics for anomaly detection models, and how does this compare across multimodal and language-only models?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.7/10.