Metode Decision Tree Algoritma C.45 Dalam Mengklasifikasi Data Penjualan Bisnis Gerai Makanan Cepat Saji

Abstract

Advances in technology and information currently produces smart innovations in business, which can be called business intelligence. One that we can use is Data Mining technology in digging useful information from sales company data warehouse. The purpose of this research is to apply data mining decision decision tree algorithm C4.5 on fast food outlets business and expected to provide information in the form of sales information about food menu that most liked by customers and less popular (bestselling and less in demand). The methodology used in classifying the sales of this research uses the steps of Algorithm C.45, The process uses five steps in KDD (Knowledge Discovery in Databases), which perpetuates activities such as pre-processing, transformation, data mining, interpretation and evaluation. In addition to performing calculations manually, this research case is also tested using Rapidminer application. From the results of the experiment to find data from the sales data of fast food outlets using algorithm C4.5 results of entropy and the highest gain is 1.501991 on the Food Menu attributes on manual calculations. When using the Rapidminer application the results of the results tree as shown in Figure 3.2. Price (s) - Sold Out - Food Menu (Bento Rice = Less Selling, Chest = Laris) Weight (weight) each attribute: Price (0.738), Menu Type (0.067), Sold Number (0.156), Sales Status (0.040).