A study of algorithm selection in data mining using meta-learning

This article discusses the algorithm selection problem in data mining with the help of meta-learning. We present the issue with the help of the classification and clustering problems. In this study, we have analyzed the working of a metalearning system in connection with the classical algorithm selection problem. Various ranking combination methods available in the literature have been explored from the perspective of the measurement system. Discussion about two new ranking combination methods namely the relative ranking and the percentage ranking have been included. The study also identifies few potential challenges in relation to algorithm selection in data mining using meta-learning.