Decision Support System for Stock Prediction and Supplier Selection Using Least Square and C4.5 Algorithm

Abstract

The development of a business is duly offset with a system capable of supporting the development of the business. A distro that runs a fashion product sales business requires a system that is able to predict the amount of stock that needs to be provided for the next month. The company also needs a system capable of recommending the right supplier choice based on the company’s needs. The supplier selection is conventionally only the owner of the company that could be decisive. To improve the efficiency of the company’s work system it is necessary to have a system that becomes an alternative to supplier selection when the business owner can not do it. The least Square method is used to predict the stock needs of goods an C4.5 algorithms to provide supplier selection solution. Tests on least square method using MAPE showed mean error in odd period modeling of 3.40%, while for even period of 34.25%. The C4.5 algorithm test using cross validation showed an accuracy of 60%. Performance indicated by least square method for odd period modeling is better than modeling in even period. The C4.5 algorithm also showed good accuracy for decision support settlement.