Data preprocessing or cleansing is one of the biggest hurdles in industry for developing successful machine learning appli- cations. The process of data cleansing includes data imputa- tion, feature normalization & selection, dimensionality reduc- tion, and data balancing applications. Currently such prepro- cessing 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 inade- quacies and research challenges for solving such a problem.