Automated Data Pre-processing via Meta-learning

Abstract

Abstract. A data mining algorithm may perform differently on datasets with different characteristics, e.g., it might perform better on a dataset with continuous attributes rather than with categorical attributes, or the other way around. As a matter of fact, a dataset usually needs to be pre-processed. Taking into account all the possible pre-processing operators, there exists a staggeringly large number of alternatives and nonexperienced users become overwhelmed. We show that this problem can be addressed by an automated approach, leveraging ideas from metalearning. Specifically, we consider a wide range of data pre-processing techniques and a set of data mining algorithms. For each data mining algorithm and selected dataset, we are able to predict the transformations that improve the result of the algorithm on the respective dataset. Our approach will help non-expert users to more effectively identify the transformations appropriate to their applications, and hence to achieve improved results.

Towards big industrial data mining through explainable automated machine learning

“…Over the last few years, a plethora of AutoML systems have been developed providing partial or complete ML automation, such as Auto-sklearn [7], TPOT [8],Auto-WEKA [9], ATM [10], as well as commercial systems such as Google AutoML 1 , RapidMiner 2 , Dar-winAI 3 , and DataRobo 4 . These tools range from automatic data preprocessing [19,20], automatic feature engineering [21,22] to automatic model selection [18,23] and automatic hyper-parameters tuning [24,25]. Some approaches attempt to automatically and simultaneously choose a learning algorithm and optimize its hyper-parameters.…”

Intelligent assistance for data pre-processing

“…Otherwise, in the worst case, all the transformations may end up having the same impact. For instance, as a first approach we considered simple regression trees [24] as meta-learners, and they suffer from this problem. Their limitation is that they contain a discrete number of leaves, and hence a discrete number of possible predictions.…”

PRESISTANT: Data Pre-processing Assistant

“…However, in our previous works [2,4,5], we showed that meta-learning can also be used to provide support specifically in the pre-processing step. This can be done by learning the impact of data pre-processing operators on the final result of the analysis.…”