“…In the initial stages, researchers mainly included Neural Network (NN), Linear regression (LR), Decision Tree (DT), Support Vector machine (SVM), Discriminant Analysis (DA) and Bayesian Belief Network. Supervised learning techniques were selected for analysis more than unsupervised ones, with 65% of the articles from US, China, Taiwan and Spain [10]. A considerable number of studies that analysed the performance of classifiers on FSF detection have shown that SVM [11,12,13,14,15], NN [16,17,18,19], DT [20,21] perform well in FSF detection/prediction.…”