Natural and Engineering Sciences 43 -SHORT COMMUNICATION- Jute Yarn Consumption Prediction by Artificial Neural Network and Multilinear Regression Zeynep Didem Unutmaz Durmuşoğlu 1 , Selma Gülyeşil 1* 1 Department of Industrial Engineering, Gaziantep University, Gaziantep,Turkey Abstract In today’s increasing competitive market conditions, the companies operating in the production and service sectors should meet the demand of the customers in a timely and completely manner. Therefore, all resources (raw materials, semi-finished products, energy sources, etc.) should be planned and supplied at the right time, at the right place and at sufficient quantity based on an accurate forecast of the demand. In the literature, there have been few studies about forecasting of raw material consumption in a production sector. In this study, ANN method was employed to predict the raw material consumption of a carpet production company. The relevant variables of the actual data belonging to 2015-2016 and 2017 were used. In addition, a multiple linear regression (MLR) model was also established to compare the performance of ANN method. The results show that ANN method produces more accurate forecasts when compared to MLR method. Keywords: Artificial Neural Network (ANN), Multiple Linear Regression (MLR), Raw Material Consumption Article history: Received 15 November 2018, Accepted 25 December 2018, Available online 30 December 2018 * Corresponding Author: Selma Gulyesil, e-mail, selmagulyesil@gmail.com Supplement, 2018, 3(3): 43-53