Optimizing Iron Price Forecasting with Linear Regression Analysis and RapidMiner

Abstract

Competition in companies often occurs in price, advertising and promotion, and quality. Price is very influential on competition in a business. The price of a product is one of the things that influences buyers to want to buy a product or not; therefore, price is very important to determine. There are two objectives in this study; the first objective is to predict the right iron price to be used in the following year so that it can be used to increase the competitiveness of the company. The second objective is to determine the attributes that affect the price. This research uses a linear regression algorithm to predict prices and measure the attributes' relationship using the RapidMiner tool. RapidMiner is software that functions as a learning tool in data mining science in which various data processing models are ready to be used easily. From the test results on the training data, an accuracy value of 95% was obtained with a threshold value of 30, which stated that the results were accurate. Then, the factors that affect the price produce factors from the size variable (mm) and unit (kg); between the two variables that affect the price, there are results from the variables that most affect the price, namely size (mm). For the performance of the linear regression model calculated using the root mean square error (RMSE) produces a value of 199,291.