การใช้ K-Nearest Neighbor Algorithm เพื่อสร้างโมเดลการจำแนกรูปแบบการเรียนรู้สำหรับทำนายผลการจัดระดับมาตรฐานผลิตภัณฑ์ OTOP หัตถกรรม กลุ่มไม้

Abstract

The aim of this research is to develop a classification model for predicting standard levels of OTOP’s wood handicraft products by using the K-Nearest Neighbor (K-NN). To develop candidates of classification models, we used the analysis software Weka to apply the k-fold cross- validation method to our datasets. Then, the best K-NN from 22 product attributes were selected to be used for the models based on the Euclidean distances. The best classification model developed from the previous steps was able to predict standard levels of OTOP’s wood handicraft products with high reliability. The model reported in this study can achieve accuracy, recall, and precision at the level of 88.34%, 88.30%, and 83.4%, respectively. Our result indicates that the model with the lowest Euclidean distance in the 3 aspects above can be efficiently used for predicting standard levels of product as specified by the OTOP project.