We propose a new machine learning algorithm: meta-boosting. Using the boosting method a weak learner can be converted into a strong learner by changing the weight distribution of the training examples. It is often regarded as a method for decreasing both the bias and variance although it mainly reduces variance. Meta-learning has the advantage of coalescing the results of multiple learners to improve accuracy, which is a bias reduction method. By combing boosting algorithms with different weak learners using the meta-learning scheme, both of the bias and variance are reduced. Our experiments demonstrate that this meta-boosting algorithm not only displays superior performance than the best results of the base-learners but that it also surpasses other recent algorithms