“…Therefore, datasets of various data types (both categorical, numerical and mixed variables), application domain, number of features, ratio of feature types, class balance and kinds of data constraints are selected (see Table 2). Several of these datasets are widely used in counterfactual explanation studies like Adult [53,29,64,74,21,76,10,45], Statlog -German Credit [53,21,59,52], Breast Cancer Wisconsin (BCW) [74,5,76,4,39] and Wine [60,42,4]. Note that the number of datasets included in the papers where these algorithms have been proposed range from 1 to only 4 [53], which further motivates the need for a large-scale benchmarking study.…”