An online-tool for tuning ensemble learning algorithms
AbstractMachine learning algorithms have configurable parameters. Known as hyperparameters, they are generally used with their default settings. However, in order to increase the success of a machine learning algorithm, it is required to develop sophisticated techniques to tune hyperparameters. Tuning a machine learning algorithms need great effort. However, existing methods can only be performed via discrete programming tools. In this paper, a user-friendly hyperparameter tuning tool is proposed for ensemble learning. It encompasses selecting tuning algorithm, data set, and performance visualization. Besides them, developed tool is compatible with executing R codes to conduct big data experiments.