Garg and Kumar (Scientia Iranica, 2017, https://doi.org/ 10.24200/SCI.2017.4454) proposed some new correlation coefficient between intuitionistic fuzzy sets (IFSs). To point out the advantages of their proposed correlation coefficient over the existing correlation coefficient, Garg and Kumar applied their proposed correlation coefficient as well as the existing correlation coefficient to identify a suitable classifier for an unknown pattern, represented by an intuitionistic fuzzy set (IFS), from the known patterns, each represented by IFS. Garg and Kumar suggested that the existing correlation coefficient fails to identify a suitable classifier, whereas, the correlation coefficient, proposed by them, does not fail to identify a suitable classifier. So, it is appropriate to use the correlation coefficient, proposed by them, instead of the existing correlation coefficient. In this note, it is shown that the correlation coefficient, proposed by Garg and Kumar, also fails to identify a suitable classifier. Furthermore, it is shown that more computational efforts are required to apply the correlation coefficient, proposed by Garg and Kumar, as compared to the existing correlation coefficient. In the actual case, it is inappropriate to apply the correlation coefficient for identifying a suitable classifier.