Automated Data Cleansing through Meta-Learning

Ian Gemp, Georgios Theocharous, Mohammad Ghavamzadeh

Abstract: Data preprocessing or cleansing is one of the biggest hurdles in industry for developing successful machine learning applications.  The process of data cleansing includes data imputation, feature normalization & selection, dimensionality reduction, and data balancing applications.  Currently such preprocessing is manual.  One approach for automating this process is meta -learning.  In this paper, we experiment with state of the art meta-learning methodologies and identify the inadequacies and research challenges for solving such a problem.