Adaptive boosting with dynamic weight adjustment

TL;DR

This paper introduces an improved AdaBoost variant that dynamically adjusts instance weights based on prediction errors, enhancing accuracy and robustness in complex and noisy data scenarios.

Contribution

It proposes a novel dynamic weight adjustment method for AdaBoost, enabling better handling of complex data relations and class imbalances.

Findings

Outperforms traditional AdaBoost in accuracy

Handles noisy and imbalanced data more effectively

Provides a flexible boosting framework

Abstract

Adaptive Boosting with Dynamic Weight Adjustment is an enhancement of the traditional Adaptive boosting commonly known as AdaBoost, a powerful ensemble learning technique. Adaptive Boosting with Dynamic Weight Adjustment technique improves the efficiency and accuracy by dynamically updating the weights of the instances based on prediction error where the weights are updated in proportion to the error rather than updating weights uniformly as we do in traditional Adaboost. Adaptive Boosting with Dynamic Weight Adjustment performs better than Adaptive Boosting as it can handle more complex data relations, allowing our model to handle imbalances and noise better, leading to more accurate and balanced predictions. The proposed model provides a more flexible and effective approach for boosting, particularly in challenging classification tasks.