SOUL: Scala Oversampling and Undersampling Library for imbalance classification

The improvements in technology and computation have promoted a global adoption of Data Science. It is devoted to extracting significant knowledge from high amounts information by means the application Artificial Intelligence Machine Learning tools. Among different tasks within Science, classification probably most widespread overall. Focusing on scenario, we often face some datasets which number instances for one classes much lower than that remaining ones. This issue known as imbalanced problem, it mainly related need boosting recognition minority class examples. In spite large solutions were proposed specialized literature address classification, there lack open-source software compiles relevant ones an easy-to-use scalable way. this paper, present novel approach named SOUL, stands Scala Oversampling Undersampling Library classification. main capabilities new library include data preprocessing techniques, efficient execution these approaches, graphical environment contrast output solutions.