Similarity Learning on Big Data: A Case Study

Abstract

: The current article aims to analyze student performance using some similarity measures. The analysis will result in a classification of the student based on how they usually take their lunch. Throughout the processes, we define some notions of similarity measures and finally select some measures to evaluate various data types of attributes. The Nearest-Neighbor approach is used for classification, with the K-Nearest-Neighbor (KNN) algorithm. At last we compare the performance on three data types: numerical, categorical and mixed data. Finally, the result is tested and validated using the Python programming language.