Application of Data Mining in Optimization of Hotel's Food and Beverage Costs

Abstract

Optimized costs could increase hotel revenue. However, based on observations, there are various methods that can be used in cost optimization, this indicating the possibility that there are other methods that can be used for this purpose. This study aims to propose application of data mining using the K-Nearest Neighbor (KNN) method to optimize costs by classifying feasibility of addition of raw materials for food and beverages based on data such as number of requests, supplies, usage, and purchases. Data used in this study is raw materials data for hotel food and beverage during January and February 2019 which amount to 152 data. Furthermore, data cleaning process applied to eliminate incomplete and duplicated data. This process produces 99 data that has been clean. Based on results of application and testing of the KNN method using confusion matrix, it is known that the value of k = 3 gives the best classification accuracy results of 80%. Then the classification results are represented in the form of graphs that are used as a basis for consideration of cost control. Based on this study, it was concluded that data mining using KNN method can be used in optimization of Hotel's Food and Beverage Costs