Meta-learning Approach for Automatic Parameter Tuning: A case of study with educational datasets

This paper proposes to the use of a meta-learning approach for automatic parameter tuning of a well-known decision tree algorithm by using past information about algorithm executions. Fourteen educational datasets were analysed using various combinations of parameter values to examine the effects of the parameter values on accuracy classification. Then, the new metadataset was used to predict the classification accuracy on the basis of the value parameters and some characteristics of the dataset. The obtained classification models can help us decide how the default parameters should be tuned in order to increase the accuracy of the classifier when using different types of educational datasets.