Favorite Lecturer Determination of UPI YPTK Padang using Apriori Algorithm

Abstract

In this study, the authors used a priori algorithm to analyze the favorite lecturer indicators of UPI YPTK students in Padang. A priori algorithm was chosen because of its ability to analyze data that appears simultaneously and repeatedly and data that has accumulated a long time, so it is necessary to use data mining, to gain knowledge. The data that I use is a selection of favorite lecturer indicators UPI YPTK Padang randomly as many as 17. The research method that I use is to manually calculate data then a trial of the Weka data mining software is conducted. The results of this study found that the pattern of determining the favorite lecturers of upi yptk padang using a priori algorithm is 10 knowledge and the items that appear are smart (1), interesting (3) and humorous (6). ). Therefore, the university leadership can give direction to the new lecturers that: if they are already smart (1) then it is suggested to be interesting (3) and / or humorous (6) and vice versa. This knowledge is very useful for improving the performance of lecturers and student interest in learning Upi Yptk Padang. This study produces 10 new rules that meet the minimum value of support (20%) and minimum confidence (55%).