This paper introduces a novel adaptive synthetic (ADASYN) sampling approach for learning from imbalanced datasets. ADASYN addresses the challenge of class imbalance by generating synthetic data samples for minority class examples, with more synthetic data allocated to those that are harder to learn. The method reduces the bias introduced by class imbalance and adaptively shifts the classification decision boundary towards difficult examples. The effectiveness of ADASYN is demonstrated through experimental results on five evaluation metrics, showing improved performance compared to existing methods. The paper also discusses the potential extensions of ADASYN to ensemble learning, multi-class imbalanced learning, and incremental learning scenarios.This paper introduces a novel adaptive synthetic (ADASYN) sampling approach for learning from imbalanced datasets. ADASYN addresses the challenge of class imbalance by generating synthetic data samples for minority class examples, with more synthetic data allocated to those that are harder to learn. The method reduces the bias introduced by class imbalance and adaptively shifts the classification decision boundary towards difficult examples. The effectiveness of ADASYN is demonstrated through experimental results on five evaluation metrics, showing improved performance compared to existing methods. The paper also discusses the potential extensions of ADASYN to ensemble learning, multi-class imbalanced learning, and incremental learning scenarios.