Meta analysis on the improvisation of Fuzzy C-Least Median using Canberra distance in multiple linear regression towards Malaysian household income

Predicting the degree of ambiguity in the data is the main challenge in data clustering. Therefore, the objective of this literature review and meta-analysis is to summarise the existing research to highlight the importance of distance metrics in clustering tools. A lot of improvements have been done to both hard clustering and soft clustering. Recently, these clustering have been integrated with the Multiple Linear regression (MLR) model to achieve better performance. Data retrieval for this systematic review was carried out on May 7, 2023, using Scopus, Web of Science, Google Scholar, and ScienceDirect in compliance with PRISMA criteria. The inclusion and exclusion criteria for this analysis resulted in the inclusion of a total of 17 papers. The majority of the included research found that distance metrics do play an important role in clustering and Canberra metrics surpass Euclidean metrics capabilities while Fuzzy C-Least Median (FCLM) appears to be a more robust and accurate model than Fuzzy C-Means (FCM) clustering. This literature review and meta-analysis also found that demographic factors had a significant effect on the household income distribution in Malaysia.