THE PURPOSE OF THIS PAPER IS TO PROVIDE AN OVERVIEW OF UNOBSERVED HETEROGENEITY IN THE FIELD OF PARTIAL LEAST SQUARES STRUCTURAL EQUATION MODELING (PLS-SEM), ITS DETECTION AND CHALLENGES FOR SOCIAL SCIENCE RESEARCHERS. IN THIS STUDY, WE DESCRIBE HOW TO DETECT AND IMPROVE WITH UNOBSERVED HETEROGENEITY IN PLS-SEM USING THE PLS FINITE MIXED MEASUREMENT UNIT (FIMIX-PLS). THIS PAPER INTEGRATES THE LITERATURE OF VARIOUS DISCIPLINES SUCH AS MANAGEMENT INFORMATION SYSTEMS, MARKETING AND STATISTICS TO PROVIDE AN ADVANCED OVERVIEW OF FIMIX-PLS. BASED ON THIS REVIEW, THE PAPER PROVIDES GUIDELINES ON HOW TO APPLY THIS TECHNIQUE TO SPECIFIC RESEARCH PROBLEMS. FIMIX-PLS IS A TOOL FOR DETECTING AND IMPROVING UNOBSERVED HETEROGENEITY IN PLS-SEM AND DETERMINING THE NUMBER OF FRACTIONS USEFUL TO OBTAIN THE DATA. SINCE THE INTRODUCTION OF FIMIX-PLS, MANY TECHNIQUES HAVE BEEN DEVELOPED TO REPLACE THE HIDDEN CLASS, WHICH EXPLAIN SOME OF THE LIMITATIONS OF THIS APPROACH. FOR EXAMPLE, THESE TECHNIQUES FAIL TO ADDRESS THE HETEROGENEITY OF MEASUREMENT MODELS AND THEIR DISTRIBUTIONAL ASSUMPTIONS. THIS ARTICLE IS FIRST INTRODUCED TO RESEARCHERS WHO ARE NOT YET FAMILIAR WITH THE FIMIX-PLS METHOD. FINALLY, THE MOST ADVANCED HETEROGENEITY COPING TECHNIQUES ARE REVIEWED IN THIS PAPER TO HELP RESEARCHERS UNDERSTAND HOW TO ANALYZE, INTERPRET, AND CALCULATE ALL CRITERIA.