ANALYSIS OF APRIORI AND K-NEAREST NEIGHBOR (KNN) ALGORITHM IN RECOMMENDING APPROPRIATE LEARNING METHOD

Abstract

The study investigates the utilization of data mining techniques, especially the Apriori algorithm and K-Nearest Neighbor (KNN) classification, in recommending appropriate learning methods based on student data. The purpose of this research is to analyze patterns and groupings in students’ behavior, preferences, and academic performance to support more informed and personalized educational strategies. The Apriori algorithm is used to identify frequent associations among learning related attributes, while KNN classification helps group students with similar learning characteristics. The analysis revealed that the digital learning method is the most preferred by students, with a percentage of 84.29%, followed by the traditional lecture method at 15.70%. These results reflect a notable trend toward technology-driven, flexible learning environments, although conventional approaches continue to hold relevance for a portion of learners. The research concludes that the integration of the Apriori algorithm and KNN clustering proves to be an effective analytical framework for facilitating adaptive learning. This approach allows educators and institutions to make data-driven decisions in tailoring instructional methods that align with the diverse needs and preferences of students.