<![CDATA[K-Nearest Neighbor is a good classification technique, but judging by previous studies, the accuracy of the KNN performance obtained is still inferior to other methods. in the classification process, if some characteristics are not good it can cause errors in the new classifier. As for this study, the researcher uses the gain ratio method as a parameter to see the correlation between each attribute in the dataset, and the gain ratio serves as a weighting for each attribute so as to produce a dataset. the correct way of classifying data using the KNN method, this study is very suitable for predicting sales of spare parts at the Panasonic Service Center company, where the company experienced a decline in sales, this research is very useful for predicting sales for the following month. The results of this study produce very precise predictions of distance with an accuracy value of 13%, where the comparison of the highest accuracy value is found in the total attribute with an accuracy distance of 13%, while the lowest accuracy difference is obtained in the month and type of sales dataset with 0.08%. the overall accuracy of all datasets increases by 100% with K=3, and K=5 gets 80% accuracy. so this method can be used to make sales predictions to make it easier for the company.]]>
Copyrights © 2022
