Abstract

Abstract
Imbalanced data are present in various business sectors and must be handled with the proper resampling methods and classification algorithms. To handle imbalanced data, there are numerous resampling and learning method combinations; nonetheless, their effective use necessitates specialised knowledge. In this paper, several approaches, ranging from more accessible to more advanced in the domain of data resampling techniques, will be considered to handle imbalanced data. The application developed delivers recommendations of the most suitable combinations of techniques for a specific dataset by extracting and comparing dataset meta-feature values recorded in a knowledge base. It facilitates effortless classification and automates part of the machine learning pipeline with comparable or better results than state-of-the-art solutions and with a much smaller execution time.

Abstract

Abstract

Abstract

Abstract
To address metadata with researchers it is important to use models that include familiar domain concepts. In the Social Sciences, the DDI is a well-accepted source of such domain concepts. To create FAIR data and metadata, we need to establish a compact set of DDI elements that fit the requirements in projects and are likely to be adopted by researchers inexperienced with metadata creation. Over time, we have engaged in interviews and data description sessions with research groups in the Social Sciences, identifying a manageable DDI subset. A recent Clinical Psychology project, TOGETHER, dealing with risk assessment for hereditary cancer, considered the inclusion of a DDI subset for the production of metadata that are timely and interoperable with data publication initiatives in the same domain. Taking a DDI subset identified by the data curators, we make a preliminary assessment of its use as a realistic effort on the part of researchers, taking into consideration the metadata created in two data description sessions, the effort involved, and overall metadata quality. A follow-up questionnaire was used to assess the perspectives of researchers regarding data description.