New Ensemble Method CAMO Boosts AI Performance on Imbalanced Data

Researchers introduced CAMO, an ensemble technique that dynamically prioritizes underrepresented classes in imbalanced datasets, addressing a critical problem where traditional AI models favor majority categories. Tested across emotion detection and grammar datasets with eight language models, CAMO achieved superior macro F1-scores, offering a domain-neutral solution for real-world classification tasks with skewed class distributions.