Adaptive robust cost-sensitive online classification algorithm for class-imbalanced datasets

With the continuous development of machine learning technology, classification has become increasingly important in various fields, such as disease detection, user analysis, etc. However, traditional classification algorithms frequently encounter challenges such as class imbalances, noise and outliers, and large-scale dynamic data processing, which limit their performance in practical applications. This study presents an enhanced adaptive robust cost-sensitive online classification algorithm that dynamically adjusts the penalty coefficient according to the distribution characteristics of the data stream and the algorithm’s performance, in combination with an online learning strategy, to improve the model’s robustness in dealing with dynamic data streams, class imbalance, and noise or outliers. A series of numerical experiments and real-world applications have validated that the new algorithm can significantly enhance classification accuracy while maintaining computational efficiency. Notably, the algorithm demonstrates promising application potential in practical problems such as credit card default detection.