As research advances, the number of study articles and researchers in diverse disciplines increases, emphasizing the importance of understanding their relationships. So the number of researchers is growing in the research community, and not only that research domain is also rising in a vast area. So our aim is to establish the nature of the researcher's connection. This article focuses on established relationship between Ph.D. advisors and advisees, which can be used to construct Academic Genealogy Trees and address future research challenges. The machine learning techniques will resolve the advisoradvisee relationship. In this article, five ML techniques, i.e., Decision Tree, SVM, Naive Bayes, Logistic Regression, and Random Forest for both cases advisor findings and advisee findings. In the experiment for advisor findings, Random Forest performs better than the other four models i.e. 95.4%., and advisee findings Logistic Regression performs better than the other four models i.e. 80.2%. Finally, compare our proposed model to the baseline, which is 11% better.