In our work, we study the problem of class imbalance and provided a so called "Boosting-SVM" algorithm. This "Boosting-SVM" algorithm allows us to attack the class imbalance problem from both the data level by modifying the weights of the training data and the algorithmic level by using an SVM as the component classifier in an ensemble method. We found that our approach constitutes an improvement in prediction performance, not only for the majority class, but also for the minority class in an imbalanced data set learning scenario.