Measuring student performance based on both qualitative and quantitative factors is essential because many undergraduate students could not be able to complete their degree in recent pasts.  At present, students’ dropout rate in university is gradually increasing and many bright students sometimes just cannot cope with the universities. The first-year result of a student is very important because in the majority of cases this drives the students to be either motivated or demotivated. So, the first-year student performance of a renowned university in Bangladesh is investigated in this paper. This research is mainly based on finding the reasons for students’ different types of results and then predicting students’ performance based on those eleven significant factors. For this purpose, a popular supervised machine learning algorithm, random forests (RF) have been used for classifying students’ different levels of results and predicting students’ performances. The input dataset for both training and testing were taken by merging the values obtained from two surveys done on students and experts using fuzzy ANFIS analysis. The result exhibits that RF can perform the classification of multiple classes based on many distinguishing features with 96.88 percent accuracy. This proposed model can also be applied to predict course-wise students’ performances and its precision can also be greatly improved by adding new factors.